© 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. 71592
    Prev
    Next
    INDEX
    Explanations

    Code/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
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.79
     논
    -0.59
     beginnetje
    -0.58
     linkovi
    -0.58
    Попис
    -0.58
     intptr
    -0.57
     PagesJaunes
    -0.57
    Bronnen
    -0.57
    enderror
    -0.56
    DriverManager
    -0.55
    POSITIVE LOGITS
     ups
    0.55
     the
    0.51
     tear
    0.50
    greenrobot
    0.49
     up
    0.46
    ContentAsync
    0.46
    ups
    0.45
     rise
    0.44
     Tear
    0.43
     Cus
    0.42
    Activations Density 0.001%

    No Known Activations