© 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. 9855
    Prev
    Next
    INDEX
    Explanations

    on

    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
     الرياضيه
    -0.59
    出版年
    -0.53
    rawDesc
    -0.52
     وتسجيلات
    -0.52
    SharedDtor
    -0.51
     OnInit
    -0.50
    elemField
    -0.49
     frères
    -0.49
    quelize
    -0.48
    ruik
    -0.48
    POSITIVE LOGITS
    CopyWith
    0.56
    ỡi
    0.56
    )");
    0.52
     proportion
    0.51
    :");
    0.50
    entir
    0.50
    WriteAttribute
    0.49
    thoff
    0.49
    Betyg
    0.49
    OOTDTY
    0.49
    Activations Density 0.114%

    No Known Activations