© 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. 41069
    Prev
    Next
    INDEX
    Explanations

    ball, system

    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
     system
    -0.83
    system
    -0.71
     System
    -0.69
     SYSTEM
    -0.62
    System
    -0.60
    ngdoc
    -0.57
     صوتيه
    -0.56
    TagHelper
    -0.55
    ásban
    -0.54
    ystem
    -0.54
    POSITIVE LOGITS
     chrétienne
    0.63
     féminine
    0.62
    Становништво
    0.57
     simplu
    0.57
     suivants
    0.57
     citoy
    0.56
    rijfs
    0.56
     elétrico
    0.55
     tasche
    0.55
     arché
    0.55
    Activations Density 0.051%

    No Known Activations