© 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. 16466
    Prev
    Next
    INDEX
    Explanations

    non-standard punctuation and formatting in texts

    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
     Walkover
    -0.58
    invokeLater
    -0.54
    PyErr
    -0.53
    hésite
    -0.52
     Paglinawan
    -0.52
    তথ্যসূত্র
    -0.52
    PathVariable
    -0.51
     GLFW
    -0.51
    ностран
    -0.51
    JsonInclude
    -0.51
    POSITIVE LOGITS
    validators
    0.57
     opérateur
    0.56
    antd
    0.55
    )))));
    0.55
    atoires
    0.54
    VIAF
    0.54
    Significance
    0.54
    Portale
    0.53
    sertation
    0.53
    onomous
    0.53
    Activations Density 0.011%

    No Known Activations