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. 1-CLT-HP
    4. 12946
    Prev
    Next
    INDEX
    Explanations

    Tamil

    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
     للاسماء
    -0.60
    PyTuple
    -0.58
    entary
    -0.57
     temptation
    -0.56
    TestingModule
    -0.54
    ZoneId
    -0.54
    DockStyle
    -0.54
    نسية
    -0.54
     AssemblyCulture
    -0.54
    permitAll
    -0.53
    POSITIVE LOGITS
    évaluateur
    0.56
    цездатний
    0.56
    ArrowToggle
    0.55
    ương
    0.51
    twimg
    0.49
    anyahu
    0.49
    त्य
    0.47
     Paglinawan
    0.47
    Encode
    0.47
     Encode
    0.47
    Activations Density 0.017%

    No Known Activations