© 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. 8789
    Prev
    Next
    INDEX
    Explanations

    oro

    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
    oredCriteria
    -1.08
     дописавши
    -1.02
     يتيمه
    -1.01
    GEBURTSDATUM
    -0.93
     ujednoznacz
    -0.91
    IUrlHelper
    -0.91
    MigrationBuilder
    -0.88
    SharedDtor
    -0.81
    webElementXpaths
    -0.81
    וויק
    -0.80
    POSITIVE LOGITS
    Scénario
    0.49
     original
    0.41
     last
    0.41
     Púb
    0.41
     finishing
    0.40
    coef
    0.40
     whole
    0.39
    ായ
    0.39
     lụ
    0.39
     "%
    0.38
    Activations Density 0.030%

    No Known Activations