© 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. 4348
    Prev
    Next
    INDEX
    Explanations

    words ending in -ation

    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
     disambiguazione
    -1.09
     autorytatywna
    -1.04
     للاسماء
    -1.00
    
    -0.96
     nahilalakip
    -0.94
     ExecuteAsync
    -0.92
    ंदीखरीदारी
    -0.91
     '\\;'
    -0.90
    MessageOf
    -0.89
    TintMode
    -0.88
    POSITIVE LOGITS
     have
    0.57
     lép
    0.51
     are
    0.50
     steps
    0.49
     &$
    0.47
     ajusta
    0.45
    BackPressed
    0.44
     sanitaires
    0.43
     menek
    0.43
     give
    0.42
    Activations Density 0.010%

    No Known Activations