© 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. 29647
    Prev
    Next
    INDEX
    Explanations

    technical terms and references in programming contexts, particularly related to code and configuration syntax

    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
    HomeAsUpEnabled
    -0.73
    Retention
    -0.57
    ourcen
    -0.55
    ainville
    -0.53
    underset
    -0.50
    iecie
    -0.50
    ksom
    -0.50
     للمعارف
    -0.50
    hatsu
    -0.49
     Reverso
    -0.49
    POSITIVE LOGITS
     AssemblyCulture
    0.68
     دیکھیے
    0.66
    setItems
    0.52
     برانيه
    0.51
     Administrativna
    0.50
    ાં
    0.49
    velocityY
    0.49
    россий
    0.47
    Välislingid
    0.47
    EndContext
    0.46
    Activations Density 0.001%

    No Known Activations