© 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. 6131
    Prev
    Next
    INDEX
    Explanations

    coding

    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
    AndEndTag
    -0.63
     Jefus
    -0.60
     ſtate
    -0.59
    aarrggbb
    -0.58
     purpoſe
    -0.56
     مرئيه
    -0.56
     deſt
    -0.56
    StoryboardSegue
    -0.54
    TagHelpers
    -0.54
     pleaſure
    -0.54
    POSITIVE LOGITS
     initComponents
    0.56
    invokeLater
    0.52
     of
    0.51
     Provide
    0.48
    leh
    0.47
    дарь
    0.46
    كويكب
    0.45
     and
    0.45
     Source
    0.44
     aside
    0.44
    Activations Density 0.003%

    No Known Activations