© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94535
    Prev
    Next
    INDEX
    Explanations

    web pages/code/documentation

    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
    ChildScrollView
    -0.77
    argout
    -0.70
     متعلقه
    -0.59
     getItemId
    -0.59
    IsContent
    -0.59
    UIControlState
    -0.59
    expandindo
    -0.58
    شهاد
    -0.58
     AttributeSet
    -0.57
     MainAxisSize
    -0.56
    POSITIVE LOGITS
     transférez
    0.60
    ждествен
    0.51
    Portály
    0.50
    AndEndTag
    0.46
    ubei
    0.46
     Foer
    0.45
     Play
    0.45
    engo
    0.44
    EditorBrowsable
    0.44
     מס
    0.43
    Activations Density 0.013%

    No Known Activations