© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 94008
    Prev
    Next
    INDEX
    Explanations

    1

    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
     igång
    -0.65
    dataIndex
    -0.64
     onOptions
    -0.64
    FunctionFlags
    -0.63
    WithIOException
    -0.63
     GenerationType
    -0.60
    CodedInputStream
    -0.59
    InitVars
    -0.59
     tavola
    -0.57
    TextAppearance
    -0.57
    POSITIVE LOGITS
    原始内容存档于
    0.54
     StatefulWidget
    0.52
     SwiftUI
    0.51
     consultato
    0.50
     مشين
    0.50
    Források
    0.47
     HasFactory
    0.47
    atah
    0.47
    BoxShadow
    0.47
     von
    0.45
    Activations Density 0.447%

    No Known Activations