© 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 · 1495 ｜ Neuronpedia

Home
Gemma-2-2B
0-CLT-HP
1495

INDEX

Explanations

facade

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

er

-0.93

adays

-0.86

ed

-0.85

ergies

-0.84

 ModelExpression

-0.79

 MainAxisSize

-0.79

úgó

-0.78

Personendaten

-0.76

pertino

-0.76

tieth

-0.75

POSITIVE LOGITS

of

0.52

mia

0.51

 mode

0.49

due

0.47

he

0.47

ally

0.46

bukkit

0.46

co

0.45

ant

0.45

 vision

0.45

Activations Density 0.302%

No Known Activations