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. 22-CLT-HP
    4. 74552
    Prev
    Next
    INDEX
    Explanations

    can

    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
    原始内容存档于
    -0.61
     Loth
    -0.59
     оригіналу
    -0.52
     JpaRepository
    -0.51
    +#+#
    -0.50
     Shaker
    -0.50
    TypedDataSet
    -0.50
    VIRGO
    -0.49
     Yamato
    -0.49
     Benson
    -0.48
    POSITIVE LOGITS
    homonymie
    0.56
     ujednoznacz
    0.54
     veckan
    0.53
    :✨
    0.53
    )_/¯
    0.52
    ṃ
    0.51
    ichord
    0.49
    myModal
    0.49
    bitol
    0.49
     histoire
    0.48
    Activations Density 0.002%

    No Known Activations