© 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. 38956
    Prev
    Next
    INDEX
    Explanations

    among/even

    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
     of
    -0.67
     help
    -0.58
     StatefulWidget
    -0.56
     give
    -0.55
     HasFactory
    -0.55
     linkovi
    -0.50
     provide
    -0.49
    help
    -0.48
     bring
    -0.47
     to
    -0.47
    POSITIVE LOGITS
     Efq
    0.72
     myſelf
    0.68
    ArrowToggle
    0.64
    ."));
    0.64
    ilstein
    0.63
     SwitchCompat
    0.63
     kasarigan
    0.62
    LookAnd
    0.62
    !*\
    0.60
    PhysRevD
    0.60
    Activations Density 0.168%

    No Known Activations