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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1093
    Prev
    Next
    INDEX
    Explanations

    Vent

    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
    gis
    -2.23
    GIS
    -1.06
     gis
    -0.93
    Gis
    -0.71
     GIS
    -0.62
    DockStyle
    -0.60
    findpost
    -0.57
    rungsseite
    -0.56
    IBOutlet
    -0.55
     vezes
    -0.52
    POSITIVE LOGITS
     onOptions
    0.56
    QMetaType
    0.56
    ungeon
    0.55
    NameInMap
    0.54
     marrying
    0.53
    ngdoc
    0.53
    principalColumn
    0.52
    catori
    0.52
     Efq
    0.51
     ligiloj
    0.50
    Activations Density 0.095%

    No Known Activations