© 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
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 19181
    Prev
    Next
    INDEX
    Explanations

    operations related to file handling and data reading

    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
    ParallelGroup
    -0.58
    owol
    -0.57
    ftagPool
    -0.54
     Metab
    -0.52
    ież
    -0.51
     Expedia
    -0.51
    MENAFN
    -0.51
    Clik
    -0.49
     pleaſure
    -0.48
     noiva
    -0.47
    POSITIVE LOGITS
     fopen
    1.02
     resourceCulture
    0.83
    fopen
    0.73
     ActionResult
    0.68
    gridy
    0.64
    protoimpl
    0.64
     iprot
    0.62
    addCriterion
    0.60
    oredCriteria
    0.59
    isfile
    0.58
    Activations Density 0.010%

    No Known Activations