© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 97087
    Prev
    Next
    INDEX
    Explanations

    exp

    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
     propOrder
    -0.63
    Kanpo
    -0.62
     ivelany
    -0.60
    atrix
    -0.59
    peutic
    -0.58
    findpost
    -0.57
    出版年
    -0.56
    Diwedd
    -0.56
    earning
    -0.56
     Мексичка
    -0.56
    POSITIVE LOGITS
     crust
    0.54
     mechanisms
    0.52
     Polyp
    0.52
     pedals
    0.52
     CanadaChoose
    0.52
     foils
    0.51
     markets
    0.50
     unregulated
    0.49
     granules
    0.48
     JVM
    0.48
    Activations Density 0.107%

    No Known Activations