© 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. 20-CLT-HP
    7. 71661
    Prev
    Next
    INDEX
    Explanations

    they

    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
     مشين
    -0.73
     protoimpl
    -0.73
     he
    -0.65
    UrlResolution
    -0.64
    PerformLayout
    -0.63
    
    -0.63
    Personendaten
    -0.62
    AddTagHelper
    -0.62
    Datuak
    -0.59
     you
    -0.59
    POSITIVE LOGITS
     they
    0.87
     They
    0.70
     and
    0.66
    They
    0.65
    they
    0.64
     them
    0.62
     ними
    0.56
     mereka
    0.52
     jih
    0.51
     họ
    0.51
    Activations Density 0.000%

    No Known Activations