© 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. 0-CLT-HP
    7. 45505
    Prev
    Next
    INDEX
    Explanations

    new

    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
     autorytatywna
    -0.77
     leçon
    -0.74
     zelve
    -0.73
     chrétienne
    -0.72
     ✭✭
    -0.71
    ParallelGroup
    -0.71
     autorité
    -0.68
     chrétien
    -0.68
     étranger
    -0.67
     amitié
    -0.67
    POSITIVE LOGITS
    <bos>
    0.90
     lead
    0.54
     mergeFrom
    0.53
    Geografía
    0.50
     help
    0.49
     was
    0.48
     Centre
    0.48
     is
    0.46
     re
    0.46
     def
    0.45
    Activations Density 0.080%

    No Known Activations