© 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. 95421
    Prev
    Next
    INDEX
    Explanations

    Modifications, lectures, or the mansion

    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
    LayoutPanel
    -0.51
     Buch
    -0.50
     hall
    -0.50
    ifoli
    -0.48
     Ma
    -0.48
     Fools
    -0.48
     por
    -0.47
     Pem
    -0.47
    outheast
    -0.47
     Modified
    -0.46
    POSITIVE LOGITS
     للاسماء
    0.77
     autorytatywna
    0.74
     Waray
    0.66
     Reſ
    0.66
    StoryboardSegue
    0.65
     NSCoder
    0.65
     Anſ
    0.63
     scolas
    0.62
     '\\;'
    0.62
     ſeveral
    0.61
    Activations Density 0.550%

    No Known Activations