© 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. 1-CLT-HP
    7. 15418
    Prev
    Next
    INDEX
    Explanations

    scholar

    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
    mybatisplus
    -0.71
    슷
    -0.68
    الإنجليزية
    -0.56
     MemoryStream
    -0.54
    acij
    -0.54
    SerializeField
    -0.54
    reactstrap
    -0.52
    didSet
    -0.52
     BitmapFactory
    -0.51
    ResponseWriter
    -0.50
    POSITIVE LOGITS
    <bos>
    0.66
    tagHelperRunner
    0.60
     bezeichneter
    0.59
    batore
    0.59
     للاسماء
    0.58
    ViewFeatures
    0.55
    ']))
    0.51
    astronomie
    0.51
    PostExecute
    0.51
     برانيه
    0.51
    Activations Density 0.003%

    No Known Activations