© 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. 21672
    Prev
    Next
    INDEX
    Explanations

    references to the current module or context in programming

    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
    
    -0.79
    ThroughAttribute
    -0.78
    crollView
    -0.75
     OFDb
    -0.74
    PyExc
    -0.69
     MaterialApp
    -0.68
     "..\..\..\
    -0.66
     سكانية
    -0.66
    olism
    -0.65
    POSITIVE LOGITS
     individual
    0.54
    个
    0.50
     us
    0.50
    mela
    0.49
     major
    0.48
    hasMoreElements
    0.48
    geable
    0.47
    下一
    0.47
    個
    0.46
     me
    0.46
    Activations Density 0.007%

    No Known Activations