© 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. 71885
    Prev
    Next
    INDEX
    Explanations

    technical contexts

    np_max-act-logits · 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
    TintMode
    -0.83
     ExecuteAsync
    -0.82
    SafeMath
    -0.75
    memoized
    -0.69
     voltmeter
    -0.66
     Speeds
    -0.60
     PyLong
    -0.60
    setVerticalGroup
    -0.59
    帖最后由
    -0.59
     otomatig
    -0.59
    POSITIVE LOGITS
     on
    0.75
     On
    0.71
    On
    0.57
     onsite
    0.52
    on
    0.51
     ON
    0.50
    ons
    0.49
     ons
    0.49
     ONS
    0.47
     package
    0.46
    Activations Density 0.000%

    No Known Activations