© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 729
    Prev
    Next
    INDEX
    Explanations

    by

    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
     насељу
    -0.72
    woordig
    -0.62
     individuals
    -0.62
     mensen
    -0.57
     physicians
    -0.56
     people
    -0.56
    Menschen
    -0.56
     lawmakers
    -0.54
     unknownFields
    -0.54
    anghai
    -0.54
    POSITIVE LOGITS
    AutoresizingMask
    0.68
     oprot
    0.60
    typeparam
    0.58
     onResponse
    0.58
     estekak
    0.56
    ResponseWriter
    0.52
     Wikispecies
    0.50
    printStackTrace
    0.50
     rospy
    0.50
    XtraEditors
    0.47
    Activations Density 0.003%

    No Known Activations