© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3648
    Prev
    Next
    INDEX
    Explanations

    to

    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
    HtmlAttribute
    -0.65
    TagMode
    -0.65
     AspNetCore
    -0.63
     propOrder
    -0.61
    InjectAttribute
    -0.61
    webElementGuid
    -0.61
    ContentAsync
    -0.59
     发表于
    -0.59
     CWE
    -0.56
    ThemeOverlay
    -0.55
    POSITIVE LOGITS
     this
    0.57
     researchers
    0.56
     many
    0.55
    this
    0.54
    many
    0.54
     most
    0.51
    Researchers
    0.48
     chercheurs
    0.47
     רבים
    0.47
     myself
    0.46
    Activations Density 0.002%

    No Known Activations