© 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. 5-CLT-HP
    7. 92217
    Prev
    Next
    INDEX
    Explanations

    code or document text

    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
     resourceCulture
    -0.73
    StoreMessageInfo
    -0.56
    AccessorTable
    -0.56
     jsPsych
    -0.55
    +#+#
    -0.55
    transQ
    -0.54
     Drapeau
    -0.54
     initComponents
    -0.54
     ComVisible
    -0.54
     ProtoMessage
    -0.54
    POSITIVE LOGITS
     tacón
    0.57
     cotone
    0.55
    <table>
    0.52
    StandardCharsets
    0.51
    ViewById
    0.50
     afectadas
    0.49
    FXMLLoader
    0.48
    InlineData
    0.47
    関連項目
    0.47
    <bos>
    0.46
    Activations Density 0.005%

    No Known Activations