© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

GEMMA-2-2B · 1-CLT-HP · 13719 ｜ Neuronpedia

Home
Gemma-2-2B
1-CLT-HP
13719

INDEX

Explanations

habit

np_max-act · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

No Configuration Found

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 habits

-0.92

habits

-0.83

 habit

-0.78

 purpoſe

-0.75

 habitudes

-0.75

 doubtnut

-0.73

 Theſe

-0.72

 pleaſure

-0.71

первых

-0.69

 Habits

-0.69

POSITIVE LOGITS

0.57

0.52

例文帳に追加

0.52

emf

0.52

0.50

0.50

my

0.48

im

0.47

0.46

stereotype

0.46

Activations Density 0.717%

No Known Activations