© 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. 45752
    Prev
    Next
    INDEX
    Explanations

    mime

    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
    MLLoader
    -0.81
    __":
    -0.79
     StatefulWidget
    -0.78
    UTELY
    -0.76
    makeConstraints
    -0.70
    رشف
    -0.70
    InstanceState
    -0.68
    quat
    -0.67
     useDispatch
    -0.66
     Remastered
    -0.66
    POSITIVE LOGITS
     käytt
    0.44
     möjlighet
    0.41
    ser
    0.40
     dekoratif
    0.39
    ArrowToggle
    0.38
     ägg
    0.38
    migrationBuilder
    0.38
     säll
    0.38
     käyttö
    0.38
     gemens
    0.38
    Activations Density 0.355%

    No Known Activations