© 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. 32439
    Prev
    Next
    INDEX
    Explanations

    closing braces and related symbols in code

    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
    AndEndTag
    -0.86
    noons
    -0.74
     بيها
    -0.74
    CppMethod
    -0.69
    FTFY
    -0.68
    ManagedBean
    -0.68
    WebServlet
    -0.67
    ècie
    -0.67
     Efq
    -0.67
    twimg
    -0.65
    POSITIVE LOGITS
    dic
    0.47
     présence
    0.46
     &$
    0.46
     Rol
    0.45
    /**
    0.44
    pil
    0.44
    ું
    0.43
    vind
    0.43
    uanya
    0.43
    <h3>
    0.43
    Activations Density 0.005%

    No Known Activations