© 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. 42397
    Prev
    Next
    INDEX
    Explanations

    times and dates

    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
    ImageContext
    -0.62
     newOwner
    -0.61
    NOPQRST
    -0.60
    ScopeManager
    -0.58
     géographique
    -0.58
    quelize
    -0.56
    RectangleBorder
    -0.56
    modb
    -0.56
     moulding
    -0.53
    degrad
    -0.51
    POSITIVE LOGITS
     also
    0.87
     can
    0.79
    <bos>
    0.77
     was
    0.75
     will
    0.73
     have
    0.67
     still
    0.65
    '
    0.65
     even
    0.63
     won
    0.63
    Activations Density 0.127%

    No Known Activations