© 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. 1-CLT-HP
    7. 8814
    Prev
    Next
    INDEX
    Explanations

    Pierre

    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
    Negative Logits
     Pierre
    -1.88
    Pierre
    -1.81
     pierre
    -0.97
    pierre
    -0.78
     PIER
    -0.70
    PIER
    -0.61
    ates
    -0.56
    parsedMessage
    -0.54
    STON
    -0.54
    ston
    -0.52
    POSITIVE LOGITS
    Personensuche
    0.87
     للاسماء
    0.81
    TagMode
    0.75
    ReusableCell
    0.68
    tableFuture
    0.64
     AssemblyTitle
    0.63
     dignité
    0.62
     mécanique
    0.62
     valmist
    0.60
     utbild
    0.59
    Activations Density 0.010%

    No Known Activations