© 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. 91108
    Prev
    Next
    INDEX
    Explanations

    brighten

    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
    memoized
    -1.00
     незавершена
    -0.93
    InjectAttribute
    -0.84
    enumi
    -0.82
    right
    -0.81
     AssemblyCompany
    -0.81
    ValueStyle
    -0.78
    OGND
    -0.77
    InvalidProtocol
    -0.76
    Према
    -0.75
    POSITIVE LOGITS
    meisterschaft
    0.48
    ΤΗ
    0.48
    Failure
    0.44
     Failure
    0.43
     failure
    0.43
    plish
    0.43
    failure
    0.42
    te
    0.42
     fail
    0.42
    g
    0.42
    Activations Density 0.082%

    No Known Activations