© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41666
    Prev
    Next
    INDEX
    Explanations

    sch

    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
    sch
    -0.75
     downs
    -0.69
    downs
    -0.69
    esch
    -0.66
     guess
    -0.64
     estimate
    -0.63
     ups
    -0.61
    انجليز
    -0.54
    estimate
    -0.53
    Downs
    -0.53
    POSITIVE LOGITS
    UpInside
    0.68
    SequentialGroup
    0.63
    TintMode
    0.63
    WillAppear
    0.62
     Customization
    0.59
     Elasticity
    0.58
    солю
    0.57
     Keim
    0.57
    PointerException
    0.56
    Twas
    0.55
    Activations Density 0.092%

    No Known Activations