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. 20-CLT-HP
    4. 74145
    Prev
    Next
    INDEX
    Explanations

    code/technical snippets

    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
    AndEndTag
    -0.54
    出版年
    -0.49
     conten
    -0.49
    通販
    -0.48
    JpaRepository
    -0.48
    ValueStyle
    -0.48
    routine
    -0.48
    makeText
    -0.45
     adultes
    -0.44
     autorité
    -0.44
    POSITIVE LOGITS
    Demografia
    0.63
     lumens
    0.56
     pips
    0.52
    Хьажоргаш
    0.51
     fathoms
    0.50
     roux
    0.50
     wavelength
    0.50
     azimuth
    0.50
     counts
    0.49
    TypedDataSet
    0.49
    Activations Density 0.001%

    No Known Activations