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. 74255
    Prev
    Next
    INDEX
    Explanations

    Code and programming

    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
     EconPapers
    -0.93
    AccessorTable
    -0.76
     InputDecoration
    -0.72
    Билгалдахарш
    -0.70
    Искәрмәләр
    -0.70
    Sucesor
    -0.67
    SBATCH
    -0.67
     estekak
    -0.66
     disambiguazione
    -0.65
     NUKAT
    -0.65
    POSITIVE LOGITS
    wel
    0.46
     Sm
    0.45
     wash
    0.43
     ujednoznacz
    0.41
     puff
    0.39
     b
    0.39
     poveznice
    0.39
    զ
    0.39
    PDF
    0.38
    init
    0.38
    Activations Density 0.016%

    No Known Activations