© 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. 15147
    Prev
    Next
    INDEX
    Explanations

    and

    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
    Portale
    -0.55
    migrationBuilder
    -0.50
    Hentet
    -0.49
    ExtendWith
    -0.48
     AssemblyTitle
    -0.48
    écart
    -0.48
     Wise
    -0.48
    erade
    -0.48
     moindre
    -0.48
    intérêt
    -0.47
    POSITIVE LOGITS
     Wikimedijinoj
    0.69
     testified
    0.61
     represented
    0.58
     functioned
    0.56
     AspNetCore
    0.56
     للمعارف
    0.55
     tasted
    0.54
     saites
    0.53
     hoeft
    0.52
     nahilalakip
    0.52
    Activations Density 0.294%

    No Known Activations