© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 95710
    Prev
    Next
    INDEX
    Explanations

    window

    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
    Negative Logits
     window
    -1.03
     Window
    -0.97
     WINDOW
    -0.83
    window
    -0.79
     fenêtre
    -0.78
    Window
    -0.77
     fenêtres
    -0.77
     aveug
    -0.77
     genoux
    -0.75
     vidrio
    -0.69
    POSITIVE LOGITS
    e
    0.98
    ed
    0.86
    i
    0.79
    maker
    0.70
    ig
    0.65
    ette
    0.63
    makers
    0.59
    ete
    0.57
    ie
    0.56
    pe
    0.56
    Activations Density 0.045%

    No Known Activations