© 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. 14970
    Prev
    Next
    INDEX
    Explanations

    references to scientific data and findings

    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
    AndEndTag
    -0.63
     Waray
    -0.57
    Interviewer
    -0.55
    ("~/
    -0.52
     Basi
    -0.51
    LLocation
    -0.51
    Orsay
    -0.50
     Jau
    -0.50
     Machia
    -0.50
     "','
    -0.49
    POSITIVE LOGITS
     autorytatywna
    0.85
    VIATIONS
    0.65
    rrggbb
    0.61
    +#+#
    0.61
    roč
    0.59
     են
    0.58
     MotionEvent
    0.57
     समीक्षाओं
    0.57
     يتيمه
    0.56
    RegressionTest
    0.53
    Activations Density 0.042%

    No Known Activations