© 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. 4-CLT-HP
    7. 116
    Prev
    Next
    INDEX
    Explanations

    scientific studies

    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
    ArrowToggle
    -0.65
    DeleteBehavior
    -0.64
    TagMode
    -0.59
    +#+#
    -0.59
    ContentAsync
    -0.57
    RegistryLite
    -0.56
     CreateTagHelper
    -0.54
     متعلقه
    -0.54
    sizeCache
    -0.54
     BorderRadius
    -0.53
    POSITIVE LOGITS
     fieldwork
    0.54
     pioneering
    0.54
     histological
    0.52
    extensive
    0.51
    Με
    0.51
    */
    0.50
     extensive
    0.49
    URLException
    0.49
     meines
    0.47
     experiments
    0.47
    Activations Density 0.007%

    No Known Activations