© 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. 20-CLT-HP
    7. 72748
    Prev
    Next
    INDEX
    Explanations

    code and XML snippets

    np_max-act-logits · 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
    ScopeManager
    -0.71
    nloa
    -0.62
     jsPsych
    -0.57
    ddot
    -0.56
     OMITBAD
    -0.55
     Réponses
    -0.54
    liyor
    -0.53
    يكب
    -0.53
     gepubliceerd
    -0.52
    Sucesor
    -0.52
    POSITIVE LOGITS
     aceptas
    0.55
    ModelBuilder
    0.50
    retty
    0.50
    cipar
    0.47
    migrationBuilder
    0.47
     UnityEditor
    0.47
     Candidates
    0.47
    ❋
    0.46
    //
    0.46
     typelib
    0.45
    Activations Density 0.004%

    No Known Activations