© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 25447
    Prev
    Next
    INDEX
    Explanations

    phrases related to making adjustments or changes, particularly in the context of following and modifying a recipe or instructions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    BeginContext
    -0.54
    älde
    -0.50
     gyhoeddwyd
    -0.47
    essero
    -0.47
     magique
    -0.47
     scolaires
    -0.45
    Unspecified
    -0.43
     vagues
    -0.43
     Dyck
    -0.42
     كمان
    -0.41
    POSITIVE LOGITS
    setAccessible
    0.78
     ویکی‌پدیا
    0.68
    UserScript
    0.61
     extra
    0.59
     customise
    0.59
     unofficial
    0.58
     ujednoznacz
    0.58
     nî
    0.58
     customised
    0.57
    ̀
    0.56
    Activations Density 0.324%

    No Known Activations