© 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. 5-CLT-HP
    7. 93475
    Prev
    Next
    INDEX
    Explanations

    Book excerpts

    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
    queryInterface
    -0.89
    aarrggbb
    -0.83
    oredCriteria
    -0.75
     '\\;'
    -0.74
     NSCoder
    -0.73
    parsedMessage
    -0.73
    abestanden
    -0.73
    ThroughAttribute
    -0.73
    elemField
    -0.70
    writerow
    -0.70
    POSITIVE LOGITS
    ":{
    0.41
    )=>{
    0.41
    事を
    0.34
    """
    0.33
    ější
    0.33
    şağı
    0.31
     raíces
    0.31
    :{
    0.30
    ней
    0.30
     ailleurs
    0.30
    Activations Density 0.003%

    No Known Activations