© 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. 4-CLT-HP
    7. 4651
    Prev
    Next
    INDEX
    Explanations

    the

    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
     preſent
    -0.54
     ſtate
    -0.50
    flink
    -0.50
    pacs
    -0.49
     atve
    -0.49
     Houſe
    -0.48
    Πηγές
    -0.48
     caractères
    -0.48
     resourceCulture
    -0.47
    Presentations
    -0.47
    POSITIVE LOGITS
    makeText
    0.66
     [*]
    0.61
     CreateTagHelper
    0.60
     nahilalakip
    0.60
    igkeit
    0.60
    IBarButtonItem
    0.51
     dafür
    0.50
     архивлан
    0.50
    KEYCODE
    0.49
    الإنجليزية
    0.49
    Activations Density 0.003%

    No Known Activations