© 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. 1-CLT-HP
    7. 9317
    Prev
    Next
    INDEX
    Explanations

    crime

    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
    MessageTagHelper
    -0.78
     ContentValues
    -0.72
    setVerticalGroup
    -0.68
    awtextra
    -0.66
    UnusedPrivate
    -0.65
    IntoConstraints
    -0.64
    sizeCache
    -0.60
    Décès
    -0.58
    Koordinaten
    -0.57
     resourceCulture
    -0.56
    POSITIVE LOGITS
    紆
    0.52
    ibility
    0.51
    osity
    0.50
    sters
    0.50
    orship
    0.49
    estão
    0.49
     Tengo
    0.48
     Veuillez
    0.48
    soort
    0.47
    bourhood
    0.47
    Activations Density 0.005%

    No Known Activations