© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

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

GEMMA-2-2B · 0-CLT-HP · 41940 ｜ Neuronpedia

Home
Gemma-2-2B
0-CLT-HP
41940

INDEX

Explanations

space and planets

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

 planet

-1.64

 planets

-1.52

 planète

-1.34

 Planets

-1.27

 PLANET

-1.18

planet

-1.16

 Roskov

-1.16

 planeta

-1.14

 planetary

-1.12

Planet

-1.09

POSITIVE LOGITS

and

0.62

0.57

’

0.57

the

0.57

in

0.56

 that

0.56

0.54

as

0.54

 which

0.54

Pal

0.54

Activations Density 0.074%

No Known Activations