© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92192
    Prev
    Next
    INDEX
    Explanations

    to

    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
    Personensuche
    -0.73
     ویکی‌پدی
    -0.70
     contextLoads
    -0.62
    rrggbb
    -0.62
    WriteTagHelper
    -0.59
    κει
    -0.58
     to
    -0.57
     scolaires
    -0.54
     programação
    -0.53
     jLabel
    -0.53
    POSITIVE LOGITS
     fiind
    0.68
     do
    0.66
     use
    0.65
     surla
    0.61
     always
    0.60
     build
    0.60
     conduct
    0.57
    tvguidetime
    0.57
     have
    0.56
     put
    0.56
    Activations Density 0.001%

    No Known Activations