© 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. 1-CLT-HP
    7. 11794
    Prev
    Next
    INDEX
    Explanations

    dockstyle

    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
     purpoſe
    -0.85
     reaſon
    -0.81
     pleaſure
    -0.79
    ſelf
    -0.78
     juſ
    -0.77
     ſever
    -0.77
    ſelves
    -0.77
     مرئيه
    -0.73
     للمعارف
    -0.72
     fevere
    -0.70
    POSITIVE LOGITS
    webElement
    0.58
    bigr
    0.53
    ťa
    0.53
    buttonBar
    0.50
    platte
    0.47
    PRNewswire
    0.45
    PYX
    0.44
     CreateTagHelper
    0.43
    сятся
    0.43
    prnewswire
    0.42
    Activations Density 1.604%

    No Known Activations