© 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. 77531
    Prev
    Next
    INDEX
    Explanations

    Legal research documents

    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
     дописавши
    -0.71
     comigo
    -0.69
     relève
    -0.67
     Roskov
    -0.66
    rrggbb
    -0.66
     CreateTagHelper
    -0.66
    گاب
    -0.66
     Италијани
    -0.65
     pingente
    -0.64
     colgantes
    -0.63
    POSITIVE LOGITS
    ;++
    0.43
     FA
    0.40
    lais
    0.38
     fed
    0.36
    кр
    0.36
    ses
    0.36
    igen
    0.36
    ulatum
    0.35
    esModule
    0.35
    FromArgb
    0.35
    Activations Density 0.003%

    No Known Activations