© 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. 94134
    Prev
    Next
    INDEX
    Explanations

    U.S. states and rules contexts

    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
     strictly
    -0.65
     Jersey
    -0.54
     York
    -0.52
    Strictly
    -0.50
    strict
    -0.50
    Jersey
    -0.47
     estrictamente
    -0.45
     JERSEY
    -0.43
    ството
    -0.42
    crollView
    -0.42
    POSITIVE LOGITS
     ExecuteAsync
    0.98
    脚注の使い方
    0.78
     Beecher
    0.75
    WebServlet
    0.73
    abetes
    0.72
     Construcción
    0.72
     StatefulWidget
    0.70
     Afonso
    0.70
     Ephe
    0.69
     RAI
    0.69
    Activations Density 0.951%

    No Known Activations