© 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. 5-CLT-HP
    7. 92908
    Prev
    Next
    INDEX
    Explanations

    se

    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
     Extragalactic
    -0.72
     légitime
    -0.50
     règle
    -0.49
    SerializedSize
    -0.48
    {}{}
    -0.48
    swatch
    -0.48
    styleType
    -0.47
     réfugiés
    -0.47
     AssemblyCulture
    -0.47
     thụ
    -0.45
    POSITIVE LOGITS
    tagHelperRunner
    0.79
    CloseOperation
    0.74
    LookAnd
    0.67
    bootstrapcdn
    0.66
     للمعارف
    0.65
    transQ
    0.63
    الحياه
    0.62
     '\\;'
    0.60
     BrowserModule
    0.60
    IBAction
    0.59
    Activations Density 0.003%

    No Known Activations