© 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 · 0-CLT-HP · 94367 ｜ Neuronpedia

Home
Gemma-2-2B
0-CLT-HP
94367

INDEX

Explanations

City

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

 myſelf

-1.72

 Monfieur

-1.68

 ainfi

-1.60

 Jefus

-1.58

 avoient

-1.55

 auroit

-1.55

 feroit

-1.55

 purpoſe

-1.55

 étoient

-1.53

 pleaſure

-1.51

POSITIVE LOGITS

Man

1.16

1.16

Bar

1.15

1.12

of

1.10

1.10

Se

1.09

1.07

1.07

1.07

Activations Density 0.439%

No Known Activations