© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 75516
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    isContained
    -0.67
    standers
    -0.56
     Eul
    -0.53
     Mahal
    -0.53
    FieldBuilder
    -0.52
    viere
    -0.52
     uintptr
    -0.51
    yons
    -0.51
     Kula
    -0.50
    isien
    -0.49
    POSITIVE LOGITS
    UrlResolution
    0.56
    devamını
    0.56
    AddHtmlAttribute
    0.52
    AILABILITY
    0.52
     bén
    0.50
    PushMatrix
    0.49
    primaryStage
    0.49
    leby
    0.49
    migrationBuilder
    0.49
     җ
    0.47
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.