© 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 · 0-CLT-HP · 93261 ｜ Neuronpedia

Home
Gemma-2-2B
0-CLT-HP
93261

INDEX

Explanations

racing

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

 race

-2.95

 Race

-2.64

Race

-2.48

race

-2.47

 races

-2.41

 RACE

-2.31

 racing

-2.28

 raced

-2.27

 Races

-2.17

RACE

-2.09

POSITIVE LOGITS

able

0.54

FormState

0.53

0.53

0.52

ette

0.50

tvguidetime

0.47

 okuyayım

0.46

 shears

0.46

waist

0.45

 vertes

0.45

Activations Density 0.513%

No Known Activations