© 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. 6064
    Prev
    Next
    INDEX
    Explanations

    code snippets related to data structure settings and configurations

    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
    ibatis
    -0.55
     IndexPath
    -0.55
      
    -0.51
    ComponentModel
    -0.51
     objectAtIndex
    -0.51
     ba
    -0.49
    </i>
    -0.49
     
    -0.49
    springframework
    -0.48
     ain
    -0.48
    POSITIVE LOGITS
    دانشنامهٔ
    1.03
    expandindo
    0.97
     itſelf
    0.94
     myſelf
    0.94
     raiſ
    0.93
     ſche
    0.91
     houſe
    0.90
    SharedDtor
    0.90
     Houſe
    0.88
     uſed
    0.86
    Activations Density 0.343%

    No Known Activations