© 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. 20476
    Prev
    Next
    INDEX
    Explanations

    headings or section titles in structured documents

    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
     Blak
    -0.79
    ———
    -0.73
     Balth
    -0.72
    वाल
    -0.71
     ComVisible
    -0.67
    csp
    -0.67
    Gras
    -0.67
    ത്ര
    -0.64
     scrive
    -0.64
    nas
    -0.63
    POSITIVE LOGITS
     ##
    1.43
    ##
    1.17
    ##
    1.14
     contextLoads
    0.98
     Dage
    0.84
    EndInit
    0.84
    ,$_
    0.81
     Anya
    0.77
    "><?=
    0.76
     tartalomajánló
    0.75
    Activations Density 0.001%

    No Known Activations