© 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. 768
    Prev
    Next
    INDEX
    Explanations

    code import statements from programming languages

    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
    ########.
    -0.70
     يتيمه
    -0.66
    LLocation
    -0.57
    AnchorTagHelper
    -0.54
    DoubleQuotes
    -0.54
     colo
    -0.51
    日閲覧
    -0.51
    bellar
    -0.50
     embri
    -0.50
    UpInside
    -0.50
    POSITIVE LOGITS
    import
    1.19
    DOCTYPE
    0.75
     RUE
    0.70
     Jodie
    0.69
     Jut
    0.68
     lò
    0.68
    glom
    0.68
    SpringBootTest
    0.66
    StoreMessageInfo
    0.66
    igrette
    0.66
    Activations Density 0.016%

    No Known Activations