© 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. 30921
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the necessity for further research or studies

    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
     tonel
    -0.65
    ASSERT
    -0.64
    WireFormat
    -0.63
    UpInside
    -0.62
     BorderRadius
    -0.62
    writeFieldEnd
    -0.61
    ip
    -0.59
     bicchiere
    -0.59
    ssf
    -0.57
    need
    -0.57
    POSITIVE LOGITS
    rungsseite
    0.77
    vedra
    0.70
    kwds
    0.67
     समीक्षक
    0.66
     unknownFields
    0.65
    kusen
    0.64
    ✨:
    0.63
    Damit
    0.63
    öglich
    0.62
     BIBSYS
    0.62
    Activations Density 0.028%

    No Known Activations