© 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. 96956
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    SourceChecksum
    -0.90
    TintMode
    -0.77
     مشين
    -0.77
    ########.
    -0.69
     kaarangay
    -0.69
     ExecuteAsync
    -0.68
    principalTable
    -0.67
     <<<<<<<<<<<<<<
    -0.67
     Italijani
    -0.66
     '{@
    -0.66
    POSITIVE LOGITS
    Hour
    0.57
    Page
    0.56
     hours
    0.51
    Hours
    0.51
    HOUR
    0.51
    hour
    0.51
     profondità
    0.50
     démocratique
    0.49
    page
    0.49
    MINUTE
    0.48
    Activations Density 0.002%

    No Known Activations