© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

GEMMA-2-2B · 1-CLT-HP · 15278 ｜ Neuronpedia

Home
Gemma-2-2B
1-CLT-HP
15278

INDEX

Explanations

N

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

-0.56

-0.54

-0.50

-0.47

 meny

-0.47

-0.46

awin

-0.42

weise

-0.42

pa

-0.41

шт

-0.41

POSITIVE LOGITS

 سكانية

0.76

+#+#

0.73

AddTagHelper

0.70

bootstrapcdn

0.66

aarrggbb

0.64

 gynhyrchwyd

0.64

,:);

0.63

المشاركات

0.61

出版年

0.60

 MERCHANTABILITY

0.59

Activations Density 0.167%

No Known Activations