© 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. 98154
    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
    misi
    -0.50
    Produzione
    -0.45
     lama
    -0.44
    naire
    -0.43
    isert
    -0.43
    ssant
    -0.42
    Distribuzione
    -0.42
     maintenance
    -0.41
    Seiten
    -0.41
    ATELY
    -0.41
    POSITIVE LOGITS
    StructEnd
    0.77
    ArgsConstructor
    0.76
    iprot
    0.75
    onViewCreated
    0.74
    InputBorder
    0.74
    GraphicsUnit
    0.73
    astéroïdes
    0.73
     NSCoder
    0.73
     تضيفلها
    0.72
    AccessorTable
    0.72
    Activations Density 0.009%

    No Known Activations