© 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. 1-CLT-HP
    7. 8652
    Prev
    Next
    INDEX
    Explanations

    code/programming

    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
     MainAxisSize
    -0.55
     ChromeDriver
    -0.52
    MethodManager
    -0.50
    #+#
    -0.49
    SourceChecksum
    -0.46
     calendriers
    -0.46
    anair
    -0.43
     kiệm
    -0.43
    TagMode
    -0.43
    Становништво
    -0.42
    POSITIVE LOGITS
    ftagPool
    0.63
     continuant
    0.60
    npmjs
    0.60
     词
    0.58
    ստ
    0.58
     perfons
    0.58
     pescoço
    0.57
    oglobulin
    0.57
    hbs
    0.56
    partic
    0.56
    Activations Density 0.023%

    No Known Activations