© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92185
    Prev
    Next
    INDEX
    Explanations

    brackets

    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
    ViewFeatures
    -0.85
     CreateTagHelper
    -0.82
     surla
    -0.82
     المعيارى
    -0.79
    存于互联网档案馆
    -0.78
     Audiodateien
    -0.78
     שוליים
    -0.77
     intptr
    -0.77
     snippetHide
    -0.73
     تضيفلها
    -0.73
    POSITIVE LOGITS
    [
    0.45
    <bos>
    0.45
     my
    0.45
    var
    0.40
    #
    0.40
    class
    0.40
    -
    0.38
    bind
    0.37
    root
    0.37
     the
    0.36
    Activations Density 1.599%

    No Known Activations