© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92244
    Prev
    Next
    INDEX
    Explanations

    behaviour

    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
     behaviour
    -0.83
     behavior
    -0.76
    tığı
    -0.55
    urcht
    -0.52
     Behavior
    -0.49
     withRouter
    -0.49
     frapp
    -0.48
    싶
    -0.47
    diğini
    -0.47
    ENZA
    -0.47
    POSITIVE LOGITS
     nahilalakip
    0.75
    apimachinery
    0.72
    Hentet
    0.66
    ########.
    0.63
     CreateTagHelper
    0.62
     Signalez
    0.61
    InvalidProtocol
    0.60
    MigrationBuilder
    0.60
     GeoNames
    0.60
    ///</
    0.59
    Activations Density 0.045%

    No Known Activations