© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4838
    Prev
    Next
    INDEX
    Explanations

    games of chance and skill

    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
    <?
    -0.66
    IBOutlet
    -0.61
     lenker
    -0.55
    جستارهای
    -0.52
    vably
    -0.51
    BITDA
    -0.49
    ceries
    -0.49
     catena
    -0.48
     uncertainty
    -0.47
     שוליים
    -0.47
    POSITIVE LOGITS
     CreateTagHelper
    0.75
    transQ
    0.68
     FetchType
    0.65
     متعلقه
    0.59
    انجليز
    0.58
     oprot
    0.57
    LookAnd
    0.54
     kommune
    0.52
    webElement
    0.52
     gynnwys
    0.50
    Activations Density 0.002%

    No Known Activations