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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 38517
    Prev
    Next
    INDEX
    Explanations

    witnessing or hearing events

    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
     heard
    -1.43
     overheard
    -1.20
     observed
    -1.17
    heard
    -1.14
     witnessed
    -1.09
    StoryboardSegue
    -1.07
    Heard
    -0.99
     Observed
    -0.98
    observed
    -0.96
     spotted
    -0.93
    POSITIVE LOGITS
     the
    0.70
    ed
    0.66
     an
    0.63
     by
    0.62
     from
    0.61
     his
    0.58
     him
    0.57
     in
    0.56
    ing
    0.54
    ers
    0.54
    Activations Density 0.037%

    No Known Activations