© 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. 15918
    Prev
    Next
    INDEX
    Explanations

    Zucker

    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
     Zucker
    -0.65
     rent
    -0.52
    etna
    -0.52
    boutin
    -0.48
     Rechnung
    -0.48
     Blech
    -0.48
    Esa
    -0.47
    deve
    -0.47
    entes
    -0.46
    styleType
    -0.46
    POSITIVE LOGITS
    :✨
    0.77
    AndEndTag
    0.75
     SafeMath
    0.65
    Ārējās
    0.60
     MainAxisSize
    0.59
     snippetHide
    0.59
    Externé
    0.55
    ValueStyle
    0.54
    ostante
    0.54
    theless
    0.54
    Activations Density 0.009%

    No Known Activations