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. 74295
    Prev
    Next
    INDEX
    Explanations

    Mixed technical/scientific language

    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
    IActionResult
    -0.54
    addCriterion
    -0.53
    MemoryWarning
    -0.52
     CascadeType
    -0.52
    odine
    -0.52
    rungsseite
    -0.52
     Winaray
    -0.51
     aDecoder
    -0.51
    make
    -0.51
     plan
    -0.50
    POSITIVE LOGITS
    principalColumn
    0.52
     introduces
    0.49
     help
    0.48
    MENAFN
    0.47
     defines
    0.46
    prüche
    0.45
     decides
    0.43
     opens
    0.43
     versions
    0.42
    babwe
    0.42
    Activations Density 0.001%

    No Known Activations