© 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. 20-CLT-HP
    7. 72666
    Prev
    Next
    INDEX
    Explanations

    Quin

    np_max-act-logits · 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
    protoimpl
    -0.82
     propOrder
    -0.81
     Италијани
    -0.81
     '\\;'
    -0.78
     convertView
    -0.69
     beginnetje
    -0.69
    Попис
    -0.68
    expandindo
    -0.68
     onOptions
    -0.64
    EndProject
    -0.64
    POSITIVE LOGITS
    sequelize
    0.45
    rawDesc
    0.43
     japoneses
    0.42
    Билгалдахарш
    0.42
    ßig
    0.41
     Japão
    0.40
    quested
    0.39
    IRD
    0.38
    erb
    0.37
     traseira
    0.37
    Activations Density 0.001%

    No Known Activations