Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 40779
    Prev
    Next
    INDEX
    Explanations

    awareness/impact

    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
    Not in Any Lists

    No Comments

    Negative Logits
     photolibrary
    -0.73
     itſelf
    -0.70
    >>()
    -0.68
     mCurrent
    -0.68
    >\<^
    -0.67
    <?
    -0.66
    >({
    -0.65
    atissimo
    -0.65
    "}")
    -0.63
    opedia
    -0.63
    POSITIVE LOGITS
     from
    0.59
    yntaxException
    0.57
     on
    0.57
    SourceChecksum
    0.57
     in
    0.54
     initComponents
    0.54
    .
    0.54
     for
    0.51
     out
    0.50
    XmlType
    0.49
    Activations Density 0.048%

    No Known Activations