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. 12828
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     Theſe
    -0.72
     Monfieur
    -0.64
     Joaquim
    -0.58
    webElementXpaths
    -0.55
    bootstrapcdn
    -0.55
     Jefus
    -0.54
     fubject
    -0.53
     Etrus
    -0.53
     Gilberto
    -0.52
     剪影
    -0.51
    POSITIVE LOGITS
     /
    0.49
     "
    0.49
     For
    0.48
     most
    0.48
     ”
    0.47
    <eos>
    0.47
     nhất
    0.47
    حياته
    0.45
     Root
    0.44
     “
    0.44
    Activations Density 0.087%

    No Known Activations