© 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. 5-CLT-HP
    7. 1219
    Prev
    Next
    INDEX
    Explanations

    computer 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
    LLocation
    -0.46
    挑战
    -0.45
     sumpay
    -0.42
    िल्
    -0.41
    rey
    -0.41
     Moulton
    -0.41
     &[
    -0.40
     communiquer
    -0.40
    hibitions
    -0.39
    ibição
    -0.39
    POSITIVE LOGITS
    Personensuche
    0.88
     getItemId
    0.82
     незавершена
    0.77
     المعيارى
    0.75
     autorytatywna
    0.73
    ]")]
    0.73
     Audiodateien
    0.70
    TagMode
    0.67
    PropertyChanging
    0.65
    %)$
    0.65
    Activations Density 0.014%

    No Known Activations