© 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. 1-CLT-HP
    7. 14321
    Prev
    Next
    INDEX
    Explanations

    lab experiments

    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
    ity
    -0.47
    ued
    -0.44
    到的
    -0.43
    led
    -0.43
    aloo
    -0.41
    ual
    -0.41
     Gutes
    -0.41
    ging
    -0.41
    hood
    -0.41
     bel
    -0.41
    POSITIVE LOGITS
    دانشنامهٔ
    1.03
    StructEnd
    0.90
    :✨
    0.88
    DockStyle
    0.86
    parsedMessage
    0.81
    WireFormatLite
    0.77
     виправивши
    0.76
     AssemblyCulture
    0.75
    getDescriptor
    0.75
    addCriterion
    0.71
    Activations Density 0.142%

    No Known Activations