© 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. 5-CLT-HP
    7. 94020
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating position

    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
    intéress
    -0.48
    cerely
    -0.47
    ttino
    -0.46
     réservation
    -0.45
     חיצוניים
    -0.44
    getProduct
    -0.43
    gamesh
    -0.43
     ıs
    -0.43
    gamon
    -0.42
     gawas
    -0.42
    POSITIVE LOGITS
    EDEFAULT
    0.75
    GEBURTSDATUM
    0.72
    unknownFields
    0.71
     the
    0.69
    CodeAnalysis
    0.65
     its
    0.63
    
    0.62
     ExecuteAsync
    0.61
    RefNanny
    0.60
    InjectAttribute
    0.60
    Activations Density 0.001%

    No Known Activations