© 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. 18788
    Prev
    Next
    INDEX
    Explanations

    elements or components related to navigation structures in a document

    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
     (
    -0.65
     in
    -0.62
     
    -0.60
     for
    -0.58
     s
    -0.57
     S
    -0.57
     E
    -0.57
     but
    -0.56
     due
    -0.56
     is
    -0.56
    POSITIVE LOGITS
     Theſe
    1.27
     Efq
    1.27
     myſelf
    1.18
     Monfieur
    1.13
     ainfi
    1.11
     auffi
    1.09
     ſeveral
    1.09
     feroit
    1.07
     pleaſure
    1.05
     auroit
    1.05
    Activations Density 0.001%

    No Known Activations