© 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. 4-CLT-HP
    7. 3152
    Prev
    Next
    INDEX
    Explanations

    scientific texts

    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
     uParam
    -0.49
     africaine
    -0.45
     públicos
    -0.45
    actus
    -0.45
    bay
    -0.44
    bula
    -0.43
    Void
    -0.43
     grecque
    -0.43
    BERRY
    -0.42
     darte
    -0.41
    POSITIVE LOGITS
    tagHelperRunner
    1.02
    MessageTagHelper
    0.81
     يتيمه
    0.78
    WebVitals
    0.77
    DoubleQuotes
    0.73
    Tikang
    0.71
    fromnode
    0.69
     المعيارى
    0.68
    bootstrapcdn
    0.66
    ValueStyle
    0.64
    Activations Density 0.020%

    No Known Activations