© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5998
    Prev
    Next
    INDEX
    Explanations

    Government, crime, legal

    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
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Vidite
    -0.71
     мәкал
    -0.68
    <bos>
    -0.65
    RetentionPolicy
    -0.62
     autorytatywna
    -0.62
     légales
    -0.60
     لينك
    -0.59
    حياته
    -0.58
     Flügel
    -0.57
    bootstrapcdn
    -0.56
    POSITIVE LOGITS
    Zunanje
    0.45
    SignedIn
    0.45
    TagHelper
    0.44
     filtering
    0.43
     quoi
    0.42
    центри
    0.42
    handleRequest
    0.41
     HasFactory
    0.40
     fuf
    0.40
    مل
    0.39
    Activations Density 0.023%

    No Known Activations