© 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. 9998
    Prev
    Next
    INDEX
    Explanations

    patterns related to structured data or formatting, such as statistical parameters or code 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
    <eos>
    -0.59
    </em>
    -0.52
    </strong>
    -0.51
     […]
    -0.48
     eccell
    -0.48
     gynhyrchwyd
    -0.43
     recruiting
    -0.43
    Diweddarwch
    -0.43
    RepeatedField
    -0.42
     ak
    -0.42
    POSITIVE LOGITS
    AutoScaleMode
    0.75
    ^(@)
    0.68
     myſelf
    0.66
    ſelves
    0.65
    tagHelperRunner
    0.63
     שוליים
    0.63
     itſelf
    0.63
     bershka
    0.61
     utafitiHapana
    0.60
    Diwedd
    0.59
    Activations Density 0.500%

    No Known Activations