© 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. 78152
    Prev
    Next
    INDEX
    Explanations

    code and technical writing

    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
    Negative Logits
    
    -0.57
    πως
    -0.57
    المناصب
    -0.55
    躇
    -0.53
    ΕΙ
    -0.50
    opropyl
    -0.47
    Salut
    -0.46
    IVEREF
    -0.46
    corbic
    -0.45
    ecap
    -0.45
    POSITIVE LOGITS
     mergeFrom
    0.55
    ybė
    0.52
     Wicidata
    0.51
     sermons
    0.49
     Duo
    0.48
     fieldNum
    0.48
    ेड
    0.47
     cholera
    0.47
     udaler
    0.47
     Lijst
    0.47
    Activations Density 0.001%

    No Known Activations