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. 11133
    Prev
    Next
    INDEX
    Explanations

    acid and related terms

    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
    Varint
    -0.77
    AxisAlignment
    -0.72
    rungsseite
    -0.70
     تضيفلها
    -0.67
    enumii
    -0.65
    Scénario
    -0.62
     <>",
    -0.60
    ftagPool
    -0.60
     OFDb
    -0.57
    __);
    -0.56
    POSITIVE LOGITS
     draw
    0.41
    Código
    0.40
     prakti
    0.40
     tắt
    0.39
     aérea
    0.39
    draws
    0.39
     jeito
    0.39
    hawatir
    0.38
    AGAT
    0.37
    draw
    0.37
    Activations Density 0.047%

    No Known Activations