© 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. 42610
    Prev
    Next
    INDEX
    Explanations

    swallows, coughing

    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
     yawn
    -1.09
    webElementXpaths
    -1.05
     cough
    -0.89
     Мексичка
    -0.87
     coughing
    -0.87
     myſelf
    -0.84
     swallow
    -0.83
     coughed
    -0.83
     swallowed
    -0.82
     asleep
    -0.81
    POSITIVE LOGITS
    ing
    0.67
     in
    0.54
     and
    0.50
    ,
    0.50
     den
    0.48
     &
    0.48
     or
    0.47
     ir
    0.46
     fur
    0.45
     Fur
    0.44
    Activations Density 1.382%

    No Known Activations