© 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. 18000
    Prev
    Next
    INDEX
    Explanations

    references to quantities, specifically measurements and weights in 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
    Not in Any Lists

    No Comments

    Negative Logits
     Ngu
    -0.60
     UNHCR
    -0.60
     registr
    -0.59
    mú
    -0.59
    ండి
    -0.58
    nicity
    -0.57
     abzu
    -0.56
     canyons
    -0.54
     Flüs
    -0.54
    QUADS
    -0.52
    POSITIVE LOGITS
     JTextArea
    0.73
    Personensuche
    0.68
    ]';
    0.66
    `;
    0.65
    WebMethod
    0.63
    rawDesc
    0.63
     FormData
    0.60
     />";
    0.59
    ogia
    0.59
     comenzado
    0.59
    Activations Density 0.018%

    No Known Activations