© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

APIAssistant AxisNEW Circuit TracerNEW Steer SAE Evals Exports Community Blog Privacy & Terms Contact

GEMMA-2-2B · 5-CLT-HP · 94984 ｜ Neuronpedia

Home
Gemma-2-2B
5-CLT-HP
94984

INDEX

Explanations

change and variation

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

esez

-0.64

vician

-0.59

cloudflare

-0.58

☸

-0.56

 mínimos

-0.54

 Италијани

-0.53

Any

-0.53

帖最后由

-0.52

correre

-0.52

lankton

-0.52

POSITIVE LOGITS

 much

0.70

 Much

0.61

much

0.60

no

0.54

Much

0.52

 that

0.48

 greatly

0.47

Activité

0.46

大大

0.45

titu

0.45

Activations Density 0.002%

No Known Activations