© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10670
    Prev
    Next
    INDEX
    Explanations

    FTC

    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
    FTC
    -1.00
    tiliz
    -0.62
     للمعارف
    -0.58
    GraphicsUnit
    -0.57
    Portale
    -0.56
     Wikimedijinoj
    -0.56
     урна
    -0.56
     Schenk
    -0.56
    igshid
    -0.54
    Mald
    -0.52
    POSITIVE LOGITS
     Madura
    0.57
    /$',
    0.55
    μως
    0.54
     Moslem
    0.54
    собенно
    0.53
    buttonShape
    0.52
    medriver
    0.50
    этому
    0.50
    chromedriver
    0.50
    Zeneca
    0.48
    Activations Density 0.038%

    No Known Activations