© 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. 828
    Prev
    Next
    INDEX
    Explanations

    formation/infrastructure

    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
     ostavi
    -0.56
    Datuak
    -0.54
    BagLayout
    -0.54
    LayoutManager
    -0.51
    nativeElement
    -0.50
    endom
    -0.50
    toThrow
    -0.50
    omitempty
    -0.49
    ugo
    -0.48
    地说道
    -0.48
    POSITIVE LOGITS
    UnitTesting
    0.61
     referenties
    0.56
     Fair
    0.55
    WebVitals
    0.53
    мії
    0.48
     efficiency
    0.47
     Referential
    0.47
     efficient
    0.47
    MemoryWarning
    0.47
     shock
    0.46
    Activations Density 0.082%

    No Known Activations