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. 10427
    Prev
    Next
    INDEX
    Explanations

    function calls related to the creation of instances or objects in programming contexts

    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
    ;#
    -0.85
     onAnimation
    -0.81
    Hozzáférés
    -0.79
    Personendaten
    -0.78
    ness
    -0.77
     ویکی‌پدیا
    -0.77
    OfYear
    -0.74
    BufferException
    -0.73
    {#
    -0.73
     unknownFields
    -0.72
    POSITIVE LOGITS
    CREATE
    0.57
    Create
    0.57
    vedi
    0.57
     Cate
    0.56
    create
    0.55
     قی
    0.54
    Cate
    0.54
     معت
    0.53
     personnaliser
    0.52
    かる
    0.51
    Activations Density 0.014%

    No Known Activations