© 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. 20-CLT-HP
    7. 72812
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    interopRequire
    -0.90
    gonic
    -0.68
    soort
    -0.68
    findpost
    -0.67
    GEBURTSDATUM
    -0.64
    __(/*!
    -0.63
    IBarButtonItem
    -0.60
     Mbps
    -0.59
    fastjson
    -0.59
    MessageOf
    -0.59
    POSITIVE LOGITS
     c
    0.79
     the
    0.59
    c
    0.59
     lights
    0.54
    cipar
    0.48
    lights
    0.44
    AllowAnonymous
    0.43
    ｃ
    0.42
     fatica
    0.42
    𝑐
    0.41
    Activations Density 0.000%

    No Known Activations