© 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. 10639
    Prev
    Next
    INDEX
    Explanations

    noteworthy or significant attributes associated with entities or concepts

    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
    XmlAccessType
    -0.66
    Xna
    -0.66
    __":
    -0.64
    <tfoot>
    -0.55
    __':
    -0.55
    __':
    -0.52
    __":
    -0.52
    AddHtmlAttribute
    -0.52
    phus
    -0.51
    ✨:
    -0.51
    POSITIVE LOGITS
     TextAppearance
    0.82
    دانشنامهٔ
    0.73
     ComVisible
    0.66
     myſelf
    0.64
    avyzd
    0.62
     themſelves
    0.61
     himſelf
    0.60
     Vedi
    0.60
     indietro
    0.59
     оригіналу
    0.59
    Activations Density 0.076%

    No Known Activations