© 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. 43862
    Prev
    Next
    INDEX
    Explanations

    brakes

    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
     disambiguazione
    -1.12
     فريبيس
    -0.93
    ьаж
    -0.89
    CloseOperation
    -0.89
    ContentAsync
    -0.88
     typelib
    -0.85
    ագրություններ
    -0.84
    ChildScrollView
    -0.84
     समीक्षक
    -0.84
    HasForeignKey
    -0.83
    POSITIVE LOGITS
    ly
    0.76
    ing
    0.63
    ary
    0.61
    ton
    0.60
    ger
    0.59
    men
    0.59
    pa
    0.59
    ken
    0.58
    pe
    0.57
    sed
    0.57
    Activations Density 0.200%

    No Known Activations