© 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. 11726
    Prev
    Next
    INDEX
    Explanations

    inequalities or expressions related to numerical limits

    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
    ."</
    -0.79
    ſelves
    -0.75
    ''');
    -0.74
    </thead>
    -0.71
     ་་
    -0.67
    enação
    -0.67
     ―――――
    -0.66
     Brahmin
    -0.66
    "</
    -0.66
    ^(@)
    -0.66
    POSITIVE LOGITS
    TagMode
    0.49
    WebElementEntity
    0.47
    vard
    0.46
    part
    0.45
     ProtoMessage
    0.44
     schia
    0.43
    bnf
    0.41
    log
    0.41
    жий
    0.41
    webElementXpaths
    0.41
    Activations Density 0.021%

    No Known Activations