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. 11180
    Prev
    Next
    INDEX
    Explanations

    speech

    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
     rağmen
    -0.50
    diffuse
    -0.49
    orianCalendar
    -0.48
    matchCondition
    -0.47
     mentales
    -0.47
     méret
    -0.46
     disparu
    -0.46
    getDeclared
    -0.46
     allergen
    -0.46
     redor
    -0.46
    POSITIVE LOGITS
    writers
    0.74
    writer
    0.73
    writing
    0.66
    inghouse
    0.64
     الرياضيه
    0.63
    WRITER
    0.62
    setVerticalGroup
    0.56
    book
    0.56
    ]-->
    0.55
    ंदीखरीदारी
    0.54
    Activations Density 0.012%

    No Known Activations