© 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. 11293
    Prev
    Next
    INDEX
    Explanations

    coding-related terms and operations, particularly in the context of programming structures and functions

    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
    positie
    -0.51
    SpringRunner
    -0.47
    mær
    -0.45
    styleUrls
    -0.44
    posi
    -0.43
    zheng
    -0.42
    UGH
    -0.40
    onded
    -0.38
    Demografia
    -0.38
    gapi
    -0.37
    POSITIVE LOGITS
    DoubleQuotes
    0.90
     ivelany
    0.74
    ########.
    0.69
    RenderAtEndOf
    0.68
    ">//
    0.66
    SuspendLayout
    0.66
    ruptedException
    0.65
    numerusform
    0.65
    AccessorTable
    0.64
    UrlResolution
    0.64
    Activations Density 0.405%

    No Known Activations