© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 38243
    Prev
    Next
    INDEX
    Explanations

    u

    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
     un
    -0.68
     u
    -0.64
     is
    -0.61
     of
    -0.57
     (
    -0.53
    是
    -0.51
     ser
    -0.50
     does
    -0.50
     a
    -0.49
     As
    -0.49
    POSITIVE LOGITS
    parsedMessage
    0.90
    URLException
    0.84
    LookAnd
    0.77
    MigrationBuilder
    0.73
    AxisAlignment
    0.70
    Etimología
    0.69
    Hentet
    0.69
     Anſ
    0.68
     okuyayım
    0.67
     AssemblyProduct
    0.67
    Activations Density 0.060%

    No Known Activations