© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 16246
    Prev
    Next
    INDEX
    Explanations

    names of people or places, particularly those in East Asian contexts

    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
    Not in Any Lists

    No Comments

    Negative Logits
    openqa
    -0.67
     Lewandowski
    -0.57
    abstractmethod
    -0.56
    IKAN
    -0.56
     genere
    -0.54
     gọn
    -0.51
    ones
    -0.51
    Exist
    -0.50
    jen
    -0.50
    請繼續往下閱讀
    -0.50
    POSITIVE LOGITS
    المناصب
    0.80
    зулта
    0.73
    StructEnd
    0.73
     Савезне
    0.69
     propOrder
    0.67
     мәкал
    0.66
    олові
    0.65
     >=",
    0.65
     zijne
    0.64
    IntoConstraints
    0.64
    Activations Density 0.006%

    No Known Activations