Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12754
    Prev
    Next
    INDEX
    Explanations

    surplus

    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
     surplus
    -1.30
     surpluses
    -1.26
     Surplus
    -1.19
    ffen
    -1.10
    AddTagHelper
    -0.74
     NSCoder
    -0.68
    WebServlet
    -0.63
    LEncoder
    -0.58
    '},
    
    -0.58
    __*/
    -0.55
    POSITIVE LOGITS
    parsedMessage
    0.57
    atify
    0.49
     trás
    0.48
    atification
    0.47
    detto
    0.47
    oubtedly
    0.46
    ását
    0.45
     Antrim
    0.45
     gebunden
    0.45
    Espero
    0.45
    Activations Density 0.004%

    No Known Activations