© 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. 5-CLT-HP
    7. 90868
    Prev
    Next
    INDEX
    Explanations

    answer

    np_max-act · 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
     InputDecoration
    -0.79
     مرئيه
    -0.63
     Roskov
    -0.62
     الاطلاع
    -0.58
     Normdatei
    -0.57
    
    -0.52
    MLLoader
    -0.51
     doInBackground
    -0.51
     Keil
    -0.49
    änien
    -0.49
    POSITIVE LOGITS
    OGND
    0.54
    WithIOException
    0.54
    twimg
    0.53
    LogFactory
    0.50
    aarrggbb
    0.48
    ็จ
    0.47
    BES
    0.47
    ệt
    0.47
     partially
    0.46
    oyant
    0.46
    Activations Density 0.004%

    No Known Activations