© 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. 91110
    Prev
    Next
    INDEX
    Explanations

    Actions and consequences

    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
    aarrggbb
    -0.67
    PreferredItem
    -0.66
    клопе
    -0.63
    ContextHolder
    -0.62
    Several
    -0.58
    :✨
    -0.58
    mergeFrom
    -0.58
     surla
    -0.57
    /*
    -0.56
    jsdelivr
    -0.54
    POSITIVE LOGITS
     their
    0.70
     up
    0.69
     the
    0.59
    up
    0.52
    their
    0.52
     themselves
    0.50
    Odkazy
    0.49
    themselves
    0.48
     Up
    0.48
    Legături
    0.46
    Activations Density 0.000%

    No Known Activations