© 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. 39984
    Prev
    Next
    INDEX
    Explanations

    field

    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
    field
    -2.58
    FIELD
    -1.84
    fields
    -1.02
     field
    -1.00
    Field
    -0.96
    feld
    -0.91
    fiel
    -0.90
    filed
    -0.86
    フィールド
    -0.85
    fie
    -0.77
    POSITIVE LOGITS
     '\\;'
    0.94
    Personensuche
    0.91
    تقاوى
    0.91
    WithIOException
    0.90
     للاسماء
    0.89
    Personendaten
    0.89
    
    0.88
    awtextra
    0.86
    MessageTagHelper
    0.85
    expandindo
    0.85
    Activations Density 0.016%

    No Known Activations