© 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. 45067
    Prev
    Next
    INDEX
    Explanations

    adult

    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
     kaarangay
    -0.77
    MethodManager
    -0.73
     ostavi
    -0.70
    ModelAdmin
    -0.69
    IntoConstraints
    -0.69
    ScopeManager
    -0.66
    NameInMap
    -0.63
    relativeTime
    -0.63
     adultos
    -0.62
     unknownFields
    -0.62
    POSITIVE LOGITS
     person
    0.62
    BorderFactory
    0.51
    NewUrlParser
    0.50
    LabelTagHelper
    0.47
     man
    0.47
     client
    0.45
    werker
    0.43
     solic
    0.42
     salesperson
    0.41
     speciation
    0.41
    Activations Density 0.078%

    No Known Activations