© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 92645
    Prev
    Next
    INDEX
    Explanations

    copy

    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
     class
    -0.96
     copy
    -0.83
     Copy
    -0.81
     copied
    -0.72
     hole
    -0.68
    Copy
    -0.65
     holes
    -0.63
     Hole
    -0.61
     COPY
    -0.61
     copying
    -0.57
    POSITIVE LOGITS
    Identyfik
    1.11
    WithIOException
    1.03
    protoimpl
    1.02
     autorytatywna
    0.99
     kaarangay
    0.89
    oredCriteria
    0.89
    featureID
    0.88
    contentLoaded
    0.87
    parsedMessage
    0.85
    EndGlobalSection
    0.85
    Activations Density 0.154%

    No Known Activations