© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 991
    Prev
    Next
    INDEX
    Explanations

    graph databases and data models

    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
    garn
    -0.43
    flexGrow
    -0.42
    MethodName
    -0.42
     garn
    -0.41
     conce
    -0.41
    affiche
    -0.40
     langer
    -0.39
     htons
    -0.39
    synthesize
    -0.39
    ียม
    -0.38
    POSITIVE LOGITS
     مشين
    0.69
    ValueStyle
    0.69
    存于互联网档案馆
    0.68
     Réponses
    0.67
    usermodel
    0.65
    malink
    0.60
    <%@
    0.60
     aDecoder
    0.60
    rungsseite
    0.60
    VersionUID
    0.60
    Activations Density 0.074%

    No Known Activations