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. 74587
    Prev
    Next
    INDEX
    Explanations

    Code files and templates

    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
     للاسماء
    -0.83
     CreateTagHelper
    -0.81
    WriteBarrier
    -0.79
    complexContent
    -0.74
    ftagPool
    -0.72
     typelib
    -0.71
     الحره
    -0.70
     FormBuilder
    -0.68
    PyExc
    -0.67
    EndContext
    -0.67
    POSITIVE LOGITS
    ,
    0.53
    .
    0.49
    แต่ง
    0.37
     lucu
    0.36
    क्टर
    0.36
    reiber
    0.35
     such
    0.35
     Meisters
    0.35
     nghiệp
    0.35
     кӀ
    0.35
    Activations Density 0.003%

    No Known Activations