© 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
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74636
    Prev
    Next
    INDEX
    Explanations

    Brooklyn

    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
    NameInMap
    -0.97
     MainAxisSize
    -0.77
    AddTagHelper
    -0.74
    GEBURTSDATUM
    -0.70
    MigrationBuilder
    -0.66
    SourceChecksum
    -0.60
    UnsafeEnabled
    -0.60
    省市镇
    -0.58
    KURZBESCHREIBUNG
    -0.58
    windowFixed
    -0.57
    POSITIVE LOGITS
     nationaux
    0.57
     nationales
    0.48
     inoxydable
    0.47
    PreExecute
    0.43
    ğından
    0.42
    warzys
    0.41
    volmente
    0.41
     मिल
    0.41
    DropDownList
    0.41
     africains
    0.40
    Activations Density 0.001%

    No Known Activations