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. 74371
    Prev
    Next
    INDEX
    Explanations

    technical/specialized topics

    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
    webElementXpaths
    -0.59
    SharedCtor
    -0.51
    memoized
    -0.45
    WireFormatLite
    -0.44
    msgTypes
    -0.43
     TextFormField
    -0.42
    xions
    -0.41
     depth
    -0.41
    buttonShape
    -0.41
    setWindow
    -0.41
    POSITIVE LOGITS
    
    0.72
     NSCoder
    0.70
    oa̍t
    0.63
     onCancelled
    0.56
     européens
    0.55
    IsContent
    0.54
     betweenstory
    0.54
    VersionUID
    0.54
     Branca
    0.54
     Wiktionnaire
    0.54
    Activations Density 0.041%

    No Known Activations