© 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. 5-CLT-HP
    7. 4372
    Prev
    Next
    INDEX
    Explanations

    to

    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
    あえて
    -0.45
    hoda
    -0.44
     resorted
    -0.42
     occurred
    -0.42
     σύ
    -0.41
     must
    -0.41
    就得
    -0.40
    除了
    -0.40
    ilya
    -0.40
    只好
    -0.40
    POSITIVE LOGITS
    MigrationBuilder
    0.90
    Portail
    0.89
     snippetHide
    0.82
    Hochspringen
    0.78
     مشين
    0.74
     iprot
    0.74
    InjectAttribute
    0.73
    SequentialGroup
    0.73
    argout
    0.72
    ScopeManager
    0.71
    Activations Density 0.030%

    No Known Activations