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. 2-GEMMASCOPE-TRANSCODER-16K
    4. 14174
    Prev
    Next
    INDEX
    Explanations

    french possessive adjectives and pronouns

    oai_token-act-pair · gemini-2.0-flash

    French possessives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_2/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    født
    -0.65
     setuptools
    -0.62
    queryInterface
    -0.59
     Monfieur
    -0.59
    XmlAccessType
    -0.59
    ValueStyle
    -0.58
    følgelig
    -0.56
     jeter
    -0.56
    berdayakan
    -0.54
    bootstrapcdn
    -0.53
    POSITIVE LOGITS
     own
    1.09
     their
    1.00
    Their
    0.92
     seu
    0.92
     his
    0.91
     ihre
    0.89
     your
    0.88
    their
    0.88
     swoje
    0.85
    Your
    0.84
    Activations Density 1.050%

    No Known Activations