© 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. 73291
    Prev
    Next
    INDEX
    Explanations

    Tested

    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
     ExecuteAsync
    -0.67
    évaluateur
    -0.66
    ंदीखरीदारी
    -0.60
    RTDA
    -0.55
     StatefulWidget
    -0.55
     Kilo
    -0.54
    hésite
    -0.53
    ########.
    -0.51
    tagHelperRunner
    -0.51
     SUDOC
    -0.50
    POSITIVE LOGITS
    Халык
    0.54
    ylum
    0.50
    práv
    0.48
     فريبيس
    0.47
     متعلقه
    0.46
    AutoField
    0.46
    tikzpicture
    0.44
    EndGlobalSection
    0.44
     مرت
    0.44
    amek
    0.44
    Activations Density 0.000%

    No Known Activations