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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13356
    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
     sanitaires
    -0.71
     giudi
    -0.67
     médicaux
    -0.65
     chrétien
    -0.63
     nødvendig
    -0.63
     aveug
    -0.62
     scolas
    -0.61
     scolaires
    -0.60
     beginning
    -0.60
     nationaux
    -0.59
    POSITIVE LOGITS
    abestanden
    0.88
    aarrggbb
    0.77
     autorytatywna
    0.77
    setupUi
    0.76
    Datuak
    0.75
    mappedBy
    0.73
    AsUp
    0.72
     emerge
    0.70
    XmlAccessType
    0.69
     argue
    0.69
    Activations Density 0.020%

    No Known Activations