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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 11315
    Prev
    Next
    INDEX
    Explanations

    specific programming commands or functions associated with stack management and variable manipulation in coding contexts

    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
     Pott
    -0.96
     Palais
    -0.94
    ècie
    -0.91
    й
    -0.90
     ProtoMessage
    -0.85
     Sapi
    -0.85
     Prada
    -0.85
     iParam
    -0.84
     tanga
    -0.84
    GOTREF
    -0.83
    POSITIVE LOGITS
     ||
    1.01
    …”
    0.73
    ap
    0.70
    ab
    0.67
    }>
    0.66
    …)
    0.65
    pl
    0.65
    ag
    0.62
    "})
    0.62
    aj
    0.61
    Activations Density 0.234%

    No Known Activations