© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

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

GEMMA-2-2B · 0-CLT-HP · 97432 ｜ Neuronpedia

Home
Gemma-2-2B
0-CLT-HP
97432

INDEX

Explanations

abbreviations

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

 InputDecoration

-0.83

MMS

-0.73

TestingModule

-0.72

 propOrder

-0.71

 itſelf

-0.70

WebVitals

-0.69

PTC

-0.69

 myſelf

-0.68

 doubtnut

-0.67

 ―――――

-0.66

POSITIVE LOGITS

0.54

0.47

Bel

0.47

0.47

0.45

bel

0.44

Ke

0.44

Mat

0.44

0.43

Cl

0.43

Activations Density 0.140%

No Known Activations