© 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. 10030
    Prev
    Next
    INDEX
    Explanations

    references to statistical results and numeric data in medical or scientific contexts

    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
     kasarigan
    -0.73
     ""],
    -0.72
    ]=>
    -0.63
    :]:
    -0.61
    IRUS
    -0.59
     merci
    -0.56
    anyahu
    -0.56
    tosí
    -0.56
    UTF
    -0.56
     illiterate
    -0.54
    POSITIVE LOGITS
    وأضاف
    0.56
    UpInside
    0.52
     including
    0.52
    tagHelperRunner
    0.49
    noscript
    0.48
    didSet
    0.47
     включая
    0.47
    یات
    0.47
    DataAnnotations
    0.46
    AZINE
    0.46
    Activations Density 0.021%

    No Known Activations