© 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. 16887
    Prev
    Next
    INDEX
    Explanations

    references to cancer-related terms and proteins significant in medical research

    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
     eigen
    -0.72
    </i>
    -0.70
     Mahat
    -0.70
    arvi
    -0.68
     paloma
    -0.67
    }");
    -0.67
     Gericht
    -0.66
    ¿½
    -0.66
    линд
    -0.66
    %)$
    -0.65
    POSITIVE LOGITS
    fcntl
    0.79
     Qi
    0.77
     Imper
    0.77
     Sewell
    0.76
    وفاته
    0.75
    Manhattan
    0.75
    avx
    0.74
     rh
    0.74
     дописавши
    0.74
     MERR
    0.73
    Activations Density 0.094%

    No Known Activations