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. 74507
    Prev
    Next
    INDEX
    Explanations

    code

    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
     ControllerBase
    -0.52
    astrar
    -0.52
     Reflex
    -0.51
    stris
    -0.50
    eddah
    -0.49
    Reflex
    -0.49
    onix
    -0.49
     Respect
    -0.48
     tartalomajánló
    -0.48
    grà
    -0.47
    POSITIVE LOGITS
    #+#
    0.50
     phy
    0.49
    InteropServices
    0.49
    !*\
    0.48
    twimg
    0.47
    Sprintf
    0.47
    出版年
    0.46
    prefixer
    0.46
    mergeFrom
    0.44
    unque
    0.43
    Activations Density 0.006%

    No Known Activations