Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 23337
    Prev
    Next
    INDEX
    Explanations

    instances of brackets or parentheses in the text

    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
     autorytatywna
    -0.58
     /\.(
    -0.52
    告
    -0.50
     poł
    -0.48
    ıy
    -0.47
    LogFactory
    -0.47
    +#+
    -0.46
    fection
    -0.46
    SFER
    -0.45
    directive
    -0.45
    POSITIVE LOGITS
    RenderAtEndOf
    0.86
    İstinadlar
    0.81
     ujednoznacz
    0.69
    Portail
    0.66
     المعيارى
    0.66
     InkWell
    0.65
    EndContext
    0.62
    MENAFN
    0.61
     referenties
    0.61
    complexContent
    0.61
    Activations Density 0.037%

    No Known Activations