© 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 · 1-CLT-HP · 45573 ｜ Neuronpedia

Home
Gemma-2-2B
1-CLT-HP
45573

INDEX

Explanations

in

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

in

-0.95

IN

-0.92

ins

-0.79

depend

-0.78

volving

-0.74

 relation

-0.70

CURS

-0.67

ín

-0.64

ordin

-0.64

inate

-0.63

POSITIVE LOGITS

 désolés

0.75

 surla

0.59

pellier

0.58

 ferdig

0.56

 للمعارف

0.56

 hoort

0.56

 mortes

0.55

raszamy

0.54

enumi

0.54

 linkovi

0.52

Activations Density 0.134%

No Known Activations