© 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. 15979
    Prev
    Next
    INDEX
    Explanations

    SA

    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
     Prussian
    -0.59
    시오
    -0.57
    CodeAttribute
    -0.56
     prière
    -0.54
     ferons
    -0.52
     مشين
    -0.50
     kapcsol
    -0.49
     cest
    -0.49
    inoa
    -0.49
     שוליים
    -0.49
    POSITIVE LOGITS
    ]--;
    0.68
    awtextra
    0.64
     BoxDecoration
    0.62
    SourceChecksum
    0.57
     propOrder
    0.57
    gonic
    0.57
    Geplaatst
    0.55
    #+#
    0.55
    styleType
    0.54
    hairs
    0.54
    Activations Density 0.060%

    No Known Activations