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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4548
    Prev
    Next
    INDEX
    Explanations

    precision

    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
     '\\;'
    -0.95
    contentLoaded
    -0.92
    Autoritní
    -0.89
    IndentedString
    -0.89
     Administrativna
    -0.75
    parsedMessage
    -0.75
     autorytatywna
    -0.74
    )";
    -0.73
     дописавши
    -0.73
    oredCriteria
    -0.70
    POSITIVE LOGITS
     like
    0.66
     be
    0.53
     a
    0.52
     what
    0.52
     to
    0.50
     about
    0.48
     fine
    0.47
     your
    0.47
     another
    0.45
     temporary
    0.45
    Activations Density 0.006%

    No Known Activations