© 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. 14501
    Prev
    Next
    INDEX
    Explanations

    XML or PHP opening tag syntax

    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
    IBinder
    -0.57
    ற
    -0.56
    Spi
    -0.52
     Luna
    -0.51
     Spi
    -0.50
    nt
    -0.49
    Luna
    -0.48
     =
    -0.48
    ela
    -0.47
    нив
    -0.47
    POSITIVE LOGITS
    <?
    1.46
    <?
    1.41
     '<?
    1.31
    "><?
    1.29
    ="<?
    1.27
    ><?
    1.24
    "?>
    1.13
     "<?
    1.10
    =<?
    0.97
     Philli
    0.96
    Activations Density 0.002%

    No Known Activations