© 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. 16928
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and commands, particularly in Python and Java

    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
    SequentialGroup
    -0.52
    IntoConstraints
    -0.52
     '{@
    -0.47
    cij
    -0.46
     APPLICABLE
    -0.45
    UMAR
    -0.45
     Ka
    -0.44
    rimid
    -0.44
     décédé
    -0.44
    Bissau
    -0.43
    POSITIVE LOGITS
    StoryboardSegue
    0.82
    MLLoader
    0.75
    findpost
    0.75
    endphp
    0.72
     AssemblyTitle
    0.71
    __':
    0.70
    OGND
    0.69
    //
    0.68
    modelBuilder
    0.65
     ligiloj
    0.65
    Activations Density 0.017%

    No Known Activations