© 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. 42607
    Prev
    Next
    INDEX
    Explanations

    descriptions

    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
    BindView
    -0.61
     vœux
    -0.58
     tilgjenge
    -0.56
     partielle
    -0.54
     enceinte
    -0.51
     jorden
    -0.51
    migrationBuilder
    -0.50
     נוס
    -0.50
     litro
    -0.50
    BindingSource
    -0.50
    POSITIVE LOGITS
    kuuta
    0.60
     autorytatywna
    0.57
    styleType
    0.56
    CloseOperation
    0.56
    RectangleBorder
    0.55
     Waray
    0.55
    roffene
    0.50
    vertret
    0.49
     الرياضيه
    0.49
    tinyos
    0.49
    Activations Density 0.008%

    No Known Activations