© 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. 12549
    Prev
    Next
    INDEX
    Explanations

    references to specific proteins associated with cellular processes

    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
     acorns
    -0.53
     preventiva
    -0.48
    ênes
    -0.46
     Argos
    -0.46
     participa
    -0.45
    schuhe
    -0.44
     distancias
    -0.43
    이션
    -0.43
    diente
    -0.41
    '\
    -0.41
    POSITIVE LOGITS
    TagMode
    0.76
    Enllaces
    0.72
    enumii
    0.71
    Бахар
    0.70
    invokeLater
    0.68
    mybatisplus
    0.67
     дописавши
    0.67
    quiel
    0.66
     defaultstate
    0.66
    Datuak
    0.63
    Activations Density 0.029%

    No Known Activations