© 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. 20-CLT-HP
    7. 71593
    Prev
    Next
    INDEX
    Explanations

    code and web snippets

    np_max-act-logits · 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
     CURIAM
    -0.75
     Himo
    -0.71
    
    -0.63
     disambiguazione
    -0.62
     AttributeSet
    -0.60
     Cancelar
    -0.58
    HAPPY
    -0.57
    abases
    -0.56
     getItemId
    -0.56
     Buena
    -0.56
    POSITIVE LOGITS
    ReusableCell
    0.50
     ro
    0.50
     {?>
    0.46
    >{@
    0.45
    PropertyGroup
    0.42
    ///</
    0.42
    ()]
    0.41
    oflu
    0.41
    csolódó
    0.41
    MigrationBuilder
    0.41
    Activations Density 0.000%

    No Known Activations