© 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. 25367
    Prev
    Next
    INDEX
    Explanations

    programming constructs and control flow statements

    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
     InputDecoration
    -0.81
    apimachinery
    -0.70
    AutoField
    -0.69
    DataAnnotations
    -0.63
     protoimpl
    -0.59
    ьаж
    -0.59
     Italijani
    -0.59
    \{\\
    -0.59
    WireFormatLite
    -0.59
    LLocation
    -0.58
    POSITIVE LOGITS
    RegressionTest
    0.58
     bezeichneter
    0.57
    Personensuche
    0.56
    ellschaft
    0.52
    evos
    0.52
    revert
    0.51
    antle
    0.49
    GEBURTSDATUM
    0.48
    ثيق
    0.48
    MathML
    0.47
    Activations Density 0.885%

    No Known Activations