© 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. 42523
    Prev
    Next
    INDEX
    Explanations

    place

    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
     place
    -0.99
    nya
    -0.61
     lugar
    -0.57
    Przypisy
    -0.50
    ses
    -0.50
    شار
    -0.48
     use
    -0.48
     Place
    -0.47
    place
    -0.46
     “
    -0.46
    POSITIVE LOGITS
     Paglinawan
    0.77
    DockStyle
    0.76
     Roskov
    0.75
    ReusableCell
    0.71
    MigrationBuilder
    0.69
     restantes
    0.68
    RenderAtEndOf
    0.67
     виправивши
    0.65
    出版年
    0.63
    THON
    0.63
    Activations Density 0.015%

    No Known Activations