© 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. 0-CLT-HP
    7. 42510
    Prev
    Next
    INDEX
    Explanations

    structure

    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
     Structure
    -0.91
     Structures
    -0.88
    STRUCTURE
    -0.88
     structure
    -0.85
     Structural
    -0.79
    Structure
    -0.79
     STRUCTURE
    -0.78
     structural
    -0.77
    structure
    -0.75
     Struktur
    -0.73
    POSITIVE LOGITS
    <bos>
    1.12
    AddHtmlAttribute
    0.63
    ThemeOverlay
    0.63
    клопе
    0.56
    enumi
    0.56
    <!
    0.54
    TintMode
    0.52
    /*!
    0.51
     ujednoznacz
    0.51
    Життєпис
    0.50
    Activations Density 0.080%

    No Known Activations