© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41741
    Prev
    Next
    INDEX
    Explanations

    broadcast

    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
     broadcast
    -1.09
    SequentialGroup
    -1.01
     Broadcast
    -1.00
    DockStyle
    -0.99
    broadcast
    -0.92
     للاسماء
    -0.91
    \{\\
    -0.89
    Broadcast
    -0.88
     EconPapers
    -0.88
     समीक्षाओं
    -0.87
    POSITIVE LOGITS
    ers
    0.73
     
    0.57
    ern
    0.56
     a
    0.54
    ness
    0.52
    ery
    0.51
    sa
    0.51
    er
    0.50
     in
    0.50
     H
    0.50
    Activations Density 1.519%

    No Known Activations