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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-CLT-HP
    4. 74318
    Prev
    Next
    INDEX
    Explanations

    butterfly

    np_max-act-logits · 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
    URLException
    -0.51
    WriteTagHelper
    -0.48
     Sal
    -0.41
     <<=
    -0.41
    exitRule
    -0.40
    WebMethod
    -0.39
    oredCriteria
    -0.39
     SAL
    -0.38
    Життєпис
    -0.38
    ti
    -0.36
    POSITIVE LOGITS
    /*
    0.68
    /**
    0.60
    EDEFAULT
    0.60
    setof
    0.60
    ToBounds
    0.60
     дописавши
    0.58
    PickerController
    0.58
    mpotent
    0.57
    Cyfeiriadau
    0.56
    脚注の使い方
    0.56
    Activations Density 0.045%

    No Known Activations