© 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. 1-CLT-HP
    7. 8975
    Prev
    Next
    INDEX
    Explanations

    medical/scientific texts

    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
    ^(@)
    -0.74
     whoſe
    -0.72
    ]--;
    -0.71
    ſelf
    -0.68
     Czar
    -0.66
    ADRID
    -0.66
     Theſe
    -0.66
     Diſ
    -0.65
     Majefty
    -0.65
    uating
    -0.65
    POSITIVE LOGITS
    io
    0.50
     to
    0.47
    ri
    0.47
    bre
    0.45
     Par
    0.45
    AddTagHelper
    0.45
     propOrder
    0.44
     Meksiku
    0.42
     Sturm
    0.41
     Te
    0.41
    Activations Density 0.020%

    No Known Activations