© 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. 1-CLT-HP
    7. 13728
    Prev
    Next
    INDEX
    Explanations

    RIG

    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
     Rig
    -0.92
    twimg
    -0.84
    Rig
    -0.81
    ArgsConstructor
    -0.67
    ContentAsync
    -0.66
     cref
    -0.60
    addContainerGap
    -0.58
    saraba
    -0.58
     estimés
    -0.58
    HtmlAttribute
    -0.57
    POSITIVE LOGITS
    ging
    0.58
    orological
    0.53
    sid
    0.50
    BGR
    0.49
    edoc
    0.48
    MigrationBuilder
    0.48
    slide
    0.48
    Démographie
    0.46
    sle
    0.45
    sil
    0.44
    Activations Density 0.008%

    No Known Activations