© 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. 8859
    Prev
    Next
    INDEX
    Explanations

    ura

    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
    Negative Logits
    ura
    -2.19
    URA
    -1.63
    uras
    -1.01
    Ura
    -0.82
     ura
    -0.81
     Ura
    -0.80
    urado
    -0.77
    aura
    -0.77
    uram
    -0.76
    oura
    -0.75
    POSITIVE LOGITS
     Meksiku
    0.59
    kheim
    0.53
    Välislingid
    0.53
    hésite
    0.52
    MigrationBuilder
    0.52
    GOTREF
    0.50
    لاعات
    0.49
    GraphicsUnit
    0.48
    TestingModule
    0.47
     Архів
    0.47
    Activations Density 0.041%

    No Known Activations