© 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. 38873
    Prev
    Next
    INDEX
    Explanations

    Bert

    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
    MigrationBuilder
    -1.20
    GEBURTSDATUM
    -0.91
     Roskov
    -0.90
    RegressionTest
    -0.88
    StoryboardSegue
    -0.87
    InitVars
    -0.86
    parsedMessage
    -0.86
     мәкал
    -0.82
    SharedDtor
    -0.82
    abestanden
    -0.80
    POSITIVE LOGITS
    ings
    0.58
    led
    0.58
    ers
    0.56
    in
    0.52
    t
    0.49
    ins
    0.48
    ERS
    0.48
    IES
    0.48
    ि
    0.47
    ler
    0.47
    Activations Density 0.074%

    No Known Activations