© 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 · 40726 ｜ Neuronpedia

Home
Gemma-2-2B
0-CLT-HP
40726

INDEX

Explanations

hal

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

hal

-2.50

hal

-2.27

HAL

-2.00

Hal

-1.89

Hal

-1.87

HAL

-1.64

hala

-1.20

halo

-1.19

halt

-1.14

hale

-1.00

POSITIVE LOGITS

 LUMP

0.70

 RSSSF

0.66

 Himo

0.63

 yoox

0.59

ñores

0.59

Efq

0.58

expandindo

0.57

 Chiara

0.57

 Roskov

0.57

 Numerade

0.56

Activations Density 0.150%

No Known Activations