© 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. 5-CLT-HP
    7. 94559
    Prev
    Next
    INDEX
    Explanations

    votes

    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
     or
    -0.38
    rican
    -0.38
    ullen
    -0.35
    sidemargin
    -0.34
    raszamy
    -0.34
    리고
    -0.33
     (
    -0.33
    textbackslash
    -0.33
    föra
    -0.32
    gely
    -0.32
    POSITIVE LOGITS
    expandindo
    0.81
    DoubleQuotes
    0.79
    migrationBuilder
    0.78
    KURZBESCHREIBUNG
    0.77
     Efq
    0.77
    IsMutable
    0.77
    ſelf
    0.76
     myſelf
    0.76
     المعيارى
    0.76
    RUnlock
    0.76
    Activations Density 0.009%

    No Known Activations