INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    61.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    references to string data types and related operations

    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -0.82
     незавершена
    -0.56
     kaarangay
    -0.51
    -0.50
     Савезне
    -0.49
     }}-
    -0.49
     noDo
    -0.48
    ]]:
    -0.47
    )',
    -0.46
    WriteTagHelper
    -0.46
    POSITIVE LOGITS
    0.47
     världen
    0.45
     coupable
    0.44
     BeautifulSoup
    0.44
     baño
    0.44
     salesman
    0.42
    Története
    0.42
    ownika
    0.41
    recette
    0.41
     obligé
    0.41
    Act Density 0.031%

    No Known Activations