© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 11026
    Prev
    Next
    INDEX
    Explanations

    code-related constructs and their syntax

    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
     contextLoads
    -0.55
     Epist
    -0.53
    ientôt
    -0.51
     epist
    -0.50
     himſelf
    -0.49
     prêtres
    -0.48
     Shakspeare
    -0.48
     šķ
    -0.48
     uſ
    -0.48
     Persön
    -0.48
    POSITIVE LOGITS
    WebVitals
    0.81
     EconPapers
    0.74
    HideFlags
    0.69
    发表于
    0.68
    CodeAttribute
    0.68
    tagHelperRunner
    0.63
    protoc
    0.62
     CreateTagHelper
    0.62
    awtextra
    0.62
     MainAxisSize
    0.61
    Activations Density 0.089%

    No Known Activations