© 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. 46052
    Prev
    Next
    INDEX
    Explanations

    Health and conditional statements

    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
     архивлан
    -0.73
    styleType
    -0.72
     intptr
    -0.65
     they
    -0.64
     you
    -0.63
    yntaxException
    -0.62
     متعلقه
    -0.60
    पया
    -0.60
     if
    -0.58
     we
    -0.54
    POSITIVE LOGITS
    🏾
    0.54
    ErrorListener
    0.53
     noastră
    0.49
     fallu
    0.49
     librement
    0.49
    BAC
    0.48
     ORD
    0.48
     jambes
    0.47
    🏿
    0.46
    bida
    0.46
    Activations Density 0.030%

    No Known Activations