© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 15764
    Prev
    Next
    INDEX
    Explanations

    scientific/technical language

    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
     الحره
    -0.77
     AssemblyCulture
    -0.67
    ">//
    -0.65
    IANGLES
    -0.61
    }{*}{
    -0.61
     autorytatywna
    -0.60
    Демографія
    -0.60
    DoubleQuotes
    -0.60
    iciaries
    -0.59
    NOPQRST
    -0.59
    POSITIVE LOGITS
    āciju
    0.51
    πως
    0.45
     Tea
    0.44
     domestiques
    0.44
    ungeon
    0.44
     Btu
    0.44
     Diretto
    0.44
     Err
    0.44
     terminée
    0.43
    TableId
    0.43
    Activations Density 0.028%

    No Known Activations