© 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. 0-CLT-HP
    7. 97743
    Prev
    Next
    INDEX
    Explanations

    Technical descriptions

    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
    Зноскі
    -0.73
     يتيمه
    -0.72
    own
    -0.69
    owns
    -0.66
    PyExc
    -0.65
     Мексичка
    -0.60
    AsUp
    -0.57
    Viitteet
    -0.56
    apimachinery
    -0.55
    gól
    -0.55
    POSITIVE LOGITS
    BagConstraints
    0.68
    :✨
    0.65
    ıyordu
    0.57
     AppDelegate
    0.54
    hen
    0.47
     DbSet
    0.47
    ıyoruz
    0.47
    ly
    0.47
    ed
    0.46
    ="@+
    0.46
    Activations Density 0.302%

    No Known Activations