© 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. 20-CLT-HP
    7. 72742
    Prev
    Next
    INDEX
    Explanations

    define

    np_max-act-logits · 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
    EndGlobalSection
    -0.53
     coq
    -0.53
    obium
    -0.53
     Kissinger
    -0.53
     kicked
    -0.51
     виправивши
    -0.50
     Naga
    -0.49
    brata
    -0.49
     Meld
    -0.49
    Boas
    -0.48
    POSITIVE LOGITS
    RenderAtEndOf
    0.53
    migrationBuilder
    0.53
    ########.
    0.52
     Lightboxes
    0.48
     leading
    0.48
     👎
    0.47
    XHR
    0.47
     stabil
    0.46
    ViewData
    0.46
    ThroughAttribute
    0.46
    Activations Density 0.000%

    No Known Activations