© 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. 10608
    Prev
    Next
    INDEX
    Explanations

    have

    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
     تضيفلها
    -0.67
     AssemblyCulture
    -0.64
    tvguidetime
    -0.63
    ագրություններ
    -0.62
     كومونز
    -0.61
    migrationBuilder
    -0.60
    anskje
    -0.59
     linkovi
    -0.59
    ConverterFactory
    -0.59
    parsedMessage
    -0.58
    POSITIVE LOGITS
     any
    1.15
    Any
    0.74
     enough
    0.69
     anyone
    0.69
    any
    0.69
     ANY
    0.67
     anys
    0.66
     anything
    0.63
     sufficient
    0.62
     Any
    0.61
    Activations Density 0.018%

    No Known Activations