© 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. 1-CLT-HP
    7. 12999
    Prev
    Next
    INDEX
    Explanations

    vastatin

    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
     Tans
    -0.87
     Ingram
    -0.82
     tans
    -0.73
     Maher
    -0.71
     Chai
    -0.70
    Chai
    -0.57
     Malone
    -0.52
     parseFrom
    -0.50
     chai
    -0.49
    siębior
    -0.49
    POSITIVE LOGITS
     defaultstate
    0.77
    QMetaType
    0.64
    VersionUID
    0.63
     nakalista
    0.63
    XmlRootElement
    0.63
    esModule
    0.62
     saites
    0.59
    sizeCache
    0.59
     Reverso
    0.57
     localObject
    0.56
    Activations Density 0.009%

    No Known Activations