© 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. 0-CLT-HP
    7. 95354
    Prev
    Next
    INDEX
    Explanations

    order

    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
     order
    -2.39
    order
    -2.00
    Order
    -1.87
     Order
    -1.87
     orders
    -1.85
     ORDER
    -1.77
     ordering
    -1.59
    ORDER
    -1.55
     ordered
    -1.54
     ordem
    -1.44
    POSITIVE LOGITS
     vindicated
    0.70
    liness
    0.69
    AndEndTag
    0.68
    InitVars
    0.66
    tagHelperRunner
    0.65
    存于互联网档案馆
    0.65
     impunity
    0.65
     prosecute
    0.64
    LookAnd
    0.64
    
    0.64
    Activations Density 0.047%

    No Known Activations