© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 30598
    Prev
    Next
    INDEX
    Explanations

    references to data partitions in processing or transformation 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
    Negative Logits
     للاسماء
    -0.90
     Roskov
    -0.90
    locene
    -0.81
     msglen
    -0.80
     espagnole
    -0.79
    derung
    -0.77
     ControllerBase
    -0.77
    velser
    -0.76
    kamen
    -0.74
    clientX
    -0.73
    POSITIVE LOGITS
     partitions
    1.48
     partition
    1.34
    partitions
    1.29
     Partition
    1.20
    partition
    1.18
    Partition
    1.12
    Partitions
    0.99
     partitioned
    0.92
     partitioning
    0.90
     Parti
    0.87
    Activations Density 0.005%

    No Known Activations