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. 15342
    Prev
    Next
    INDEX
    Explanations

    patterns related to programming language syntax and structure

    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
     CreateTagHelper
    -0.68
    ConstraintMaker
    -0.61
     autorytatywna
    -0.57
    ValueStyle
    -0.57
    Mutagenicity
    -0.48
    AddTagHelper
    -0.48
     ziren
    -0.47
    مصادر
    -0.47
    )++;
    -0.46
    ẾT
    -0.46
    POSITIVE LOGITS
     whoſe
    0.63
    таратура
    0.63
    AndView
    0.63
    hithe
    0.55
     ſmall
    0.55
     Monfieur
    0.55
     Inſ
    0.55
     Cæsar
    0.54
     ſta
    0.54
     greateſt
    0.54
    Activations Density 0.263%

    No Known Activations