© 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. 94161
    Prev
    Next
    INDEX
    Explanations

    agreement, confirmation, similarity

    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
     Italijanski
    -0.65
     Wikimedijinoj
    -0.60
    autres
    -0.58
     élevées
    -0.57
     également
    -0.57
    UserScript
    -0.57
    Diweddarwch
    -0.56
    getters
    -0.56
     andere
    -0.56
     ligiloj
    -0.55
    POSITIVE LOGITS
     neither
    0.62
     nothing
    0.57
     really
    0.56
     everything
    0.56
     none
    0.55
    alnız
    0.55
     then
    0.54
     only
    0.54
     either
    0.54
     respectively
    0.54
    Activations Density 0.030%

    No Known Activations