© 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. 20-CLT-HP
    7. 76291
    Prev
    Next
    INDEX
    Explanations

    sat

    np_max-act-logits · 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
    MigrationBuilder
    -0.83
    Datuak
    -0.81
    ValueStyle
    -0.76
    writeFieldEnd
    -0.75
    WriteBarrier
    -0.71
    Демографія
    -0.69
     BoxFit
    -0.66
    DockStyle
    -0.66
    出版年
    -0.66
    contentLoaded
    -0.64
    POSITIVE LOGITS
    nami
    0.45
    range
    0.44
     fermé
    0.44
    kari
    0.43
    vacy
    0.43
    pura
    0.43
    cipta
    0.42
     range
    0.42
    phyllum
    0.41
    tra
    0.41
    Activations Density 0.001%

    No Known Activations