© 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. 1-CLT-HP
    7. 14781
    Prev
    Next
    INDEX
    Explanations

    engage

    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
    //
    -0.69
     незавершена
    -0.64
    seamnă
    -0.61
     Verk
    -0.55
    invokeLater
    -0.55
     essentiels
    -0.54
     normaux
    -0.54
    Keb
    -0.54
    itano
    -0.54
    Rüyada
    -0.53
    POSITIVE LOGITS
     with
    0.79
     propOrder
    0.65
    AsUp
    0.55
     kasarigan
    0.50
     isComment
    0.50
     Damit
    0.47
     transférez
    0.46
    elfde
    0.46
     Infórmanos
    0.45
    Produzione
    0.45
    Activations Density 0.050%

    No Known Activations