CLT Features Sharpen the Cyclical Day-of-Week Manifold in Gemma-2-2b

·LessWrong··

tl;dr: I reproduced the Goodfire lab's cyclical manifold result using days-of-the-week on Gemma-2-2b and found that Anthropic's pre-trained CLT features produce an even cleaner cyclical manifold with more distinct features than the raw activations or output probabilities. Colab notebook implementation can be found here.IntroductionIn May of this year, Wurgaft et al. (2026) reproduced a known result that days-of-the-week (and other semantically cyclical and sequential relationships) are represent...

Read full article →

Related Articles

US strikes $1.2B deal to pay German firm to halt offshore wind projects
defrost · Hacker News · 20h ago
Oracle bans AI-generated code from OpenJDK
delduca · Hacker News · 13h ago
AMD acquires Taalas to boost inference performance by etching models in silicon
itvision · Hacker News · 1d ago
Making Postgres 300x faster for analytics: batching, operator fusion, and SIMD
poly2it · Hacker News · 19h ago
Qwen3.8 Max now ranked as the best overall model by agentic index
apitman · Hacker News · 1d ago