© 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. 28710
    Prev
    Next
    INDEX
    Explanations

    references to system blocks and their superblocks in data structures

    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
    awat
    -0.71
     dgv
    -0.68
     Auguste
    -0.67
     sze
    -0.65
     Kapoor
    -0.61
    nessed
    -0.60
     oblig
    -0.60
     Coates
    -0.59
    Fcn
    -0.59
     Bruch
    -0.58
    POSITIVE LOGITS
     sb
    1.29
     Sb
    1.15
     SB
    1.10
    sb
    1.06
    SB
    1.02
    Sb
    0.98
     fantasmas
    0.74
     avancé
    0.73
     Raiders
    0.72
     Stearns
    0.72
    Activations Density 0.006%

    No Known Activations