© 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. 15926
    Prev
    Next
    INDEX
    Explanations

    head

    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
     head
    -0.89
    head
    -0.86
    Head
    -0.78
     Head
    -0.77
    HEAD
    -0.71
    الإنجليزية
    -0.68
     HEAD
    -0.68
    heads
    -0.62
     विश्वसनीयता
    -0.56
    UnsafeEnabled
    -0.54
    POSITIVE LOGITS
    !*\
    0.60
    -------
    0.59
    SharedCtor
    0.53
    InBackground
    0.49
     envió
    0.49
     memainkan
    0.49
    xymatrix
    0.48
    ρχ
    0.48
    folio
    0.47
     Descartes
    0.47
    Activations Density 0.007%

    No Known Activations