© 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. 14771
    Prev
    Next
    INDEX
    Explanations

    problem

    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
     pokok
    -0.52
     við
    -0.49
     jorden
    -0.49
    ulement
    -0.47
     akong
    -0.46
    ssä
    -0.46
     vanligt
    -0.46
     semula
    -0.45
     ifrån
    -0.45
     tryck
    -0.44
    POSITIVE LOGITS
    EDEFAULT
    0.82
    IntoConstraints
    0.79
    InvalidProtocol
    0.77
    SharedCtor
    0.73
    hoga
    0.71
     noqa
    0.69
    Tikang
    0.69
     للاسماء
    0.67
    RenderAtEndOf
    0.66
     pinulongan
    0.65
    Activations Density 0.006%

    No Known Activations