© 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. 0-CLT-HP
    7. 42887
    Prev
    Next
    INDEX
    Explanations

    timeless

    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
    Ex
    -0.58
     eternal
    -0.51
    ex
    -0.47
     eternally
    -0.46
     immortal
    -0.46
    mp
    -0.46
    ho
    -0.45
    es
    -0.45
     everlasting
    -0.44
    pr
    -0.42
    POSITIVE LOGITS
    }{*}{}
    0.77
     CURIAM
    0.76
    webElement
    0.75
    riors
    0.73
     Gelatin
    0.70
    ,:),
    0.69
    XmlAccessType
    0.68
     ExecuteAsync
    0.68
    visiae
    0.67
    logeny
    0.67
    Activations Density 0.333%

    No Known Activations