© 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. 24905
    Prev
    Next
    INDEX
    Explanations

    technical or scientific terms related to medical research and statistical analysis

    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
     religieuses
    -0.50
     dentaire
    -0.50
     cuisson
    -0.46
     sanitarias
    -0.46
     culturelles
    -0.44
     vuelto
    -0.42
    gação
    -0.41
     anlam
    -0.40
     bonté
    -0.40
     acrílico
    -0.40
    POSITIVE LOGITS
    EndProject
    0.79
    Personensuche
    0.79
    ftagPool
    0.77
     صوتيه
    0.73
     intptr
    0.71
    mybatisplus
    0.70
     typelib
    0.68
     utafitiHapana
    0.66
    +#+
    0.66
    rativa
    0.66
    Activations Density 0.037%

    No Known Activations