© 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. 5-CLT-HP
    7. 91174
    Prev
    Next
    INDEX
    Explanations

    sports, clubs, country

    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
     kasarigan
    -0.93
    WebElementEntity
    -0.83
    expandindo
    -0.81
     propOrder
    -0.81
     protoimpl
    -0.75
     Мексичка
    -0.73
    GEBURTSDATUM
    -0.71
     Bioaccumulative
    -0.70
    Portale
    -0.69
    IsContent
    -0.66
    POSITIVE LOGITS
    ’
    0.63
    '
    0.60
     efforts
    0.47
    ,
    0.46
     esfuerzos
    0.45
     усилия
    0.40
    .
    0.40
     they
    0.40
     situation
    0.39
     endeavours
    0.39
    Activations Density 0.011%

    No Known Activations