© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43007
    Prev
    Next
    INDEX
    Explanations

    interrupt

    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
     closed
    -1.33
     Closure
    -1.23
     closure
    -1.23
     Closed
    -1.20
    closed
    -1.15
     interrupt
    -1.13
     closures
    -1.11
     CLOSED
    -1.11
     interrupting
    -1.11
     fermée
    -1.11
    POSITIVE LOGITS
    es
    0.78
     the
    0.76
    ה
    0.68
     your
    0.64
    e
    0.63
    o
    0.63
    oom
    0.62
    ی
    0.61
     an
    0.59
    eing
    0.59
    Activations Density 0.042%

    No Known Activations