© 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. 77033
    Prev
    Next
    INDEX
    Explanations

    Technical context

    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
    脚注の使い方
    -0.71
    LookAnd
    -0.65
    Viitteet
    -0.62
    EndGlobalSection
    -0.60
     defaultstate
    -0.59
    MigrationBuilder
    -0.58
    TypedDataSet
    -0.57
    Entrée
    -0.57
    esModule
    -0.56
    StoryboardSegue
    -0.54
    POSITIVE LOGITS
     in
    0.61
    rinfo
    0.48
     Fib
    0.46
    czar
    0.45
     htons
    0.44
     بع
    0.44
     away
    0.42
    ิลปะ
    0.42
    Fib
    0.42
    UAR
    0.41
    Activations Density 0.001%

    No Known Activations