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. 12869
    Prev
    Next
    INDEX
    Explanations

    Internet

    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
    RenderAtEndOf
    -0.56
     Internet
    -0.52
     network
    -0.51
    network
    -0.49
     internet
    -0.48
    IntoConstraints
    -0.46
     networks
    -0.45
     []:
    -0.44
    网络
    -0.44
    :✨
    -0.43
    POSITIVE LOGITS
     Мексичка
    0.71
    IndentedString
    0.65
     stack
    0.63
    jooq
    0.63
    Попис
    0.62
     }{@
    0.60
    MessageOf
    0.59
    ########.
    0.59
    #+#
    0.57
     $#
    0.57
    Activations Density 0.136%

    No Known Activations