© 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. 76355
    Prev
    Next
    INDEX
    Explanations

    XML code

    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
    MigrationBuilder
    -0.77
     ModelExpression
    -0.75
     saites
    -0.66
    InjectAttribute
    -0.62
     ligiloj
    -0.62
     المعيارى
    -0.61
     Wiktionnaire
    -0.60
    ondissement
    -0.60
    ContentAsync
    -0.60
    TypedDataSet
    -0.59
    POSITIVE LOGITS
    Intermediate
    0.47
    $_['
    0.45
     kautta
    0.43
     intermédiaire
    0.43
     Intermediate
    0.42
    intermediate
    0.41
     bambou
    0.40
    opatra
    0.39
    aqu
    0.38
    newArrayList
    0.38
    Activations Density 0.001%

    No Known Activations