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. 11140
    Prev
    Next
    INDEX
    Explanations

    do

    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
    GHIJKLM
    -0.47
     LOGGER
    -0.44
     MRI
    -0.44
     stakeholder
    -0.44
    uku
    -0.44
    étaient
    -0.43
     micro
    -0.42
     interactive
    -0.42
     BPA
    -0.42
    chapper
    -0.42
    POSITIVE LOGITS
    Referensi
    0.63
    nalités
    0.60
    ressum
    0.56
    ఔ
    0.55
     @"/
    0.54
    ituary
    0.54
    hdashline
    0.54
    Хьажоргаш
    0.54
    TagMode
    0.54
    Nuorodos
    0.53
    Activations Density 0.004%

    No Known Activations