© 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. 20-CLT-HP
    7. 77337
    Prev
    Next
    INDEX
    Explanations

    PAR/par

    np_max-act-logits · 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
     autorytatywna
    -0.87
    ThroughAttribute
    -0.86
    MigrationBuilder
    -0.83
    RegressionTest
    -0.82
    IContainer
    -0.82
     Италијани
    -0.79
    webElementXpaths
    -0.79
    principalTable
    -0.77
    IUrlHelper
    -0.76
     Савезне
    -0.75
    POSITIVE LOGITS
     PAR
    0.61
     in
    0.58
     Par
    0.51
    PAR
    0.50
    Par
    0.48
     par
    0.47
     //
    0.46
    //
    0.41
    par
    0.40
    lops
    0.39
    Activations Density 0.003%

    No Known Activations