© 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. 5600
    Prev
    Next
    INDEX
    Explanations

    references to datasets in computational 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
    findpost
    -0.77
    ChildScrollView
    -0.73
    fromCharCode
    -0.70
     surla
    -0.69
    ";}
    -0.68
    MENAFN
    -0.68
    //
    -0.67
     onOptions
    -0.65
    IContainer
    -0.63
    SpringRunner
    -0.63
    POSITIVE LOGITS
     dataset
    0.72
    dataset
    0.63
     Dataset
    0.61
     Datasets
    0.60
    数据集
    0.60
    Dataset
    0.60
     datasets
    0.60
    DataSet
    0.59
    WithEmail
    0.57
    datasets
    0.54
    Activations Density 0.193%

    No Known Activations