© 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. 71658
    Prev
    Next
    INDEX
    Explanations

    to

    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
    WriteTagHelper
    -0.74
     useRouter
    -0.70
    AddHtmlAttribute
    -0.69
     مرئيه
    -0.66
     utafiti
    -0.65
    ThroughAttribute
    -0.63
     betweenstory
    -0.63
    SourceChecksum
    -0.62
    struzioni
    -0.60
    Παραπομπές
    -0.59
    POSITIVE LOGITS
     do
    0.74
     conduct
    0.66
     direct
    0.55
    do
    0.54
    conduct
    0.54
     perfect
    0.53
    Do
    0.52
     Do
    0.52
    DO
    0.48
     DO
    0.48
    Activations Density 0.004%

    No Known Activations