© 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 · 1-CLT-HP · 698 ｜ Neuronpedia

Home
Gemma-2-2B
1-CLT-HP
698

INDEX

Explanations

logged

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

athers

-0.95

ather

-0.64

zło

-0.63

 AssemblyCulture

-0.63

 متعلقه

-0.62

+#+#

-0.62

Билгалдахарш

-0.61

verwijspagina

-0.61

ATHER

-0.60

ſelves

-0.60

POSITIVE LOGITS

0.59

piac

0.47

sqlite

0.47

RS

0.47

sulf

0.47

uroy

0.46

sme

0.45

smb

0.45

sans

0.45

sul

0.44

Activations Density 0.017%

No Known Activations