© 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. 14997
    Prev
    Next
    INDEX
    Explanations

    references to the PDF file format and its associated functionalities

    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
    TypedDataSet
    -0.89
    orology
    -0.78
    SBATCH
    -0.74
    teck
    -0.74
    ="#"><
    -0.72
    cales
    -0.71
     Corsa
    -0.71
    lusconi
    -0.70
    apollo
    -0.69
     թվական
    -0.69
    POSITIVE LOGITS
     PDF
    0.65
    PDF
    0.60
     pdf
    0.60
     PDFs
    0.60
    ftagPool
    0.55
    pdf
    0.52
    PutMapping
    0.49
     indisponible
    0.48
    ()?;
    0.48
    Pdf
    0.46
    Activations Density 0.006%

    No Known Activations