© 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. 20087
    Prev
    Next
    INDEX
    Explanations

    syntactic structures related to programming and data organization

    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
    Datuak
    -0.75
     Italij
    -0.73
     Majefty
    -0.71
    RegistryLite
    -0.70
     vorbei
    -0.68
    expandindo
    -0.68
     deschis
    -0.68
     становника
    -0.66
    Geplaatst
    -0.64
     PREF
    -0.64
    POSITIVE LOGITS
     all
    0.49
    rited
    0.48
     related
    0.48
    sed
    0.46
     cu
    0.45
     let
    0.44
    нрави
    0.44
     pure
    0.44
     de
    0.44
    ან
    0.44
    Activations Density 0.102%

    No Known Activations