© 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. 9015
    Prev
    Next
    INDEX
    Explanations

    pending

    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
     pending
    -1.46
     Pending
    -1.27
    pending
    -1.27
    Pending
    -1.09
     незавершена
    -0.81
    PENDING
    -0.78
    mani
    -0.72
    RenderAtEndOf
    -0.71
    HasAnnotation
    -0.66
     فريبيس
    -0.60
    POSITIVE LOGITS
     Lage
    0.57
    CodeAnalysis
    0.56
    enumii
    0.54
    Lage
    0.52
    apture
    0.52
    cetamol
    0.50
    참고
    0.50
    łos
    0.50
    enumi
    0.50
     scoper
    0.49
    Activations Density 0.014%

    No Known Activations