© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 3271
    Prev
    Next
    INDEX
    Explanations

    code

    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
     the
    -0.88
     all
    -0.73
     some
    -0.68
     any
    -0.66
     a
    -0.66
     several
    -0.66
     both
    -0.62
    %</
    -0.61
     multiple
    -0.59
     each
    -0.59
    POSITIVE LOGITS
     brancas
    0.60
    ,
    0.55
     înainte
    0.54
     للمعارف
    0.54
    :✨
    0.54
     pungkasnya
    0.53
     poitrine
    0.51
    ungguhnya
    0.51
    存于互联网档案馆
    0.50
    .
    0.50
    Activations Density 0.004%

    No Known Activations