© 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. 6120
    Prev
    Next
    INDEX
    Explanations

    in

    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
    RenderAtEndOf
    -0.63
    <bos>
    -0.62
     متعلقه
    -0.61
    HomeAsUpEnabled
    -0.60
     initComponents
    -0.58
    msford
    -0.57
     चीज़ों
    -0.56
     ddelweddau
    -0.55
     دریافت‌شده
    -0.55
     intercooler
    -0.54
    POSITIVE LOGITS
     and
    0.58
    følge
    0.49
    İstinadlar
    0.48
    Personensuche
    0.48
     sanitaires
    0.47
     or
    0.47
     mapStateToProps
    0.47
    iritto
    0.46
    商品説明
    0.46
     potenciales
    0.46
    Activations Density 0.002%

    No Known Activations