© 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. 4-CLT-HP
    7. 754
    Prev
    Next
    INDEX
    Explanations

    Code/text with punctuation

    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
     Roskov
    -0.66
    makeConstraints
    -0.65
    říklad
    -0.61
    ']));
    -0.60
    IBOutlet
    -0.59
    //});
    -0.59
    ])){
    -0.58
    migrationBuilder
    -0.57
    ')));
    -0.57
    ыгана
    -0.57
    POSITIVE LOGITS
    IGraphics
    0.57
     оригіналу
    0.49
    nya
    0.49
    ILayout
    0.47
     Verbal
    0.47
    Captor
    0.47
    routeProvider
    0.46
     Yarm
    0.45
     Storms
    0.45
    Diweddarwch
    0.43
    Activations Density 0.007%

    No Known Activations