© 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. 28707
    Prev
    Next
    INDEX
    Explanations

    phrases related to percentages or quantities associated with a result or product

    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
    Tikang
    -0.71
     ویکی‌پدیا
    -0.63
     autorytatywna
    -0.62
    cahontas
    -0.62
     tfsi
    -0.61
    curité
    -0.61
     Shakspeare
    -0.60
     Wikimedijinoj
    -0.59
     cdti
    -0.58
     Efq
    -0.57
    POSITIVE LOGITS
    ArgsConstructor
    0.67
    IsPostBack
    0.59
     BoxDecoration
    0.56
    UnsafeEnabled
    0.50
    oredCriteria
    0.49
    endregion
    0.49
    sizeCache
    0.49
    TimeUnit
    0.48
    經過
    0.47
    Viitteet
    0.47
    Activations Density 0.174%

    No Known Activations