© 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. 15084
    Prev
    Next
    INDEX
    Explanations

    repeated elements or patterns in a structured format, likely related to programming or design specification

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Slowly
    -0.56
    PageRoute
    -0.56
    phene
    -0.52
     shutil
    -0.48
    çük
    -0.48
     själva
    -0.48
     cutters
    -0.47
    ējās
    -0.47
     Barracks
    -0.47
     Poitiers
    -0.45
    POSITIVE LOGITS
    mybatisplus
    0.98
    DockStyle
    0.93
    addCriterion
    0.84
    endphp
    0.84
    writeFieldEnd
    0.82
    errHandler
    0.74
    hyrchwyd
    0.72
    ContentAsync
    0.71
    GOTREF
    0.71
     صوتيه
    0.70
    Activations Density 0.001%

    No Known Activations