© 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. 4-CLT-HP
    7. 361
    Prev
    Next
    INDEX
    Explanations

    the

    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
    WriteLiteral
    -0.63
    ⓘ
    -0.62
    PMailer
    -0.59
     propOrder
    -0.56
     contactos
    -0.54
    featureID
    -0.54
    MLLoader
    -0.53
    Atsauces
    -0.53
     שוליים
    -0.53
    yship
    -0.53
    POSITIVE LOGITS
    BASEPATH
    0.57
    CloseOperation
    0.55
     one
    0.54
    styleType
    0.53
     artific
    0.52
    protoc
    0.51
     */;
    0.49
     Olímpicos
    0.47
     linkovi
    0.47
     fevere
    0.47
    Activations Density 0.003%

    No Known Activations