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. 12848
    Prev
    Next
    INDEX
    Explanations

    beauty

    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
     AssemblyCulture
    -0.90
     OFDb
    -0.70
    AccessorTable
    -0.60
     WebDriverWait
    -0.53
    tzmann
    -0.52
    ViewImports
    -0.52
    JpaRepository
    -0.51
    thâu
    -0.49
     &_
    -0.49
    verständlich
    -0.49
    POSITIVE LOGITS
     Kerja
    0.64
     koš
    0.50
     fair
    0.50
    fony
    0.47
    """.
    0.47
     faire
    0.46
    issory
    0.46
    świ
    0.45
     cooper
    0.45
    hace
    0.45
    Activations Density 0.002%

    No Known Activations