© 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. 20559
    Prev
    Next
    INDEX
    Explanations

    references to API documentation and associated links

    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
    Hochspringen
    -0.77
    الحياه
    -0.64
     Wied
    -0.58
     Eſ
    -0.57
    ſelf
    -0.53
     houſe
    -0.53
     Prophe
    -0.51
     themſelves
    -0.50
    jede
    -0.49
     iſt
    -0.49
    POSITIVE LOGITS
     CreateTagHelper
    0.73
     Paglinawan
    0.71
    AnchorTagHelper
    0.66
    WriteTagHelper
    0.65
    fromnode
    0.62
    fecture
    0.60
     localVar
    0.57
     ApiException
    0.57
     @"/
    0.57
    Caprio
    0.57
    Activations Density 0.002%

    No Known Activations