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. 0-CLT-HP
    4. 40811
    Prev
    Next
    INDEX
    Explanations

    .\

    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
    ,
    -0.79
     so
    -0.73
     then
    -0.71
     at
    -0.71
     in
    -0.67
     as
    -0.66
     and
    -0.66
     on
    -0.65
     to
    -0.64
     or
    -0.64
    POSITIVE LOGITS
    protoimpl
    1.06
     Roskov
    1.06
     Theſe
    1.05
     disambiguazione
    1.00
     Shakspeare
    0.99
    expandindo
    0.99
    MockBean
    0.98
    Vidite
    0.98
    دانشنامهٔ
    0.96
    AddTagHelper
    0.95
    Activations Density 0.021%

    No Known Activations