© 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. 59
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax elements related to programming interfaces and functions

    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
    <eos>
    -0.77
    ).
    -0.56
     nakalista
    -0.56
    ↵↵
    -0.53
    ↵↵↵
    -0.52
    ".
    -0.50
    ló
    -0.50
     modern
    -0.49
    =='
    -0.48
     gu
    -0.48
    POSITIVE LOGITS
    tagHelperRunner
    0.87
     propOrder
    0.85
     createState
    0.82
     CreateTagHelper
    0.79
    DoubleQuotes
    0.78
    Hentet
    0.77
     AssemblyCulture
    0.75
     useAppContext
    0.74
     FetchType
    0.73
     typelib
    0.70
    Activations Density 6.649%

    No Known Activations