© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 40434
    Prev
    Next
    INDEX
    Explanations

    fluorine

    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
    voort
    -0.59
    hei
    -0.53
     ne
    -0.52
     fri
    -0.49
     vic
    -0.49
    fri
    -0.49
    Immutable
    -0.49
    latimes
    -0.48
    holi
    -0.47
    ικ
    -0.47
    POSITIVE LOGITS
    setVerticalGroup
    0.88
    RenderAtEndOf
    0.79
    IUrlHelper
    0.76
    HtmlAttribute
    0.73
    Enllaces
    0.71
     myſelf
    0.70
    DoubleQuotes
    0.70
    tagHelperRunner
    0.69
     Numerade
    0.69
     becauſe
    0.67
    Activations Density 0.223%

    No Known Activations