© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 26759
    Prev
    Next
    INDEX
    Explanations

    variable names and data structures in code-like language

    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
    databind
    -0.54
    EndContext
    -0.52
     do
    -0.52
    Obrázky
    -0.46
    ActionPerformed
    -0.45
     doing
    -0.43
     weet
    -0.43
    Przypisy
    -0.41
    露天
    -0.40
    do
    -0.40
    POSITIVE LOGITS
    MigrationBuilder
    0.94
    TagMode
    0.87
    ValueStyle
    0.75
     ExecuteAsync
    0.73
    ]='\
    0.67
     المعيارى
    0.65
    ötzlich
    0.65
    __':
    0.65
    __':
    0.63
     microfilm
    0.62
    Activations Density 0.019%

    No Known Activations