© 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. 30329
    Prev
    Next
    INDEX
    Explanations

    numerical codes or identifiers related to technical specifications

    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
    IsMutable
    -0.65
    tagHelperRunner
    -0.62
    ValueStyle
    -0.59
    awtextra
    -0.56
    setVerticalGroup
    -0.55
     manches
    -0.54
    ExecuteReader
    -0.54
    beginTransaction
    -0.54
    OrBuilder
    -0.52
     colère
    -0.52
    POSITIVE LOGITS
     Roskov
    0.70
    vician
    0.57
     Италијани
    0.52
     trasc
    0.51
    chartInstance
    0.51
    ագրություններ
    0.51
    enumi
    0.50
     MRT
    0.50
    vanna
    0.50
    مراجع
    0.49
    Activations Density 0.014%

    No Known Activations