© 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. 21007
    Prev
    Next
    INDEX
    Explanations

    references to specific chemical suppliers and reagents

    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
    principalTable
    -0.85
    Jeografia
    -0.70
    ="#"><
    -0.68
    posedge
    -0.64
    ixeira
    -0.61
    arakhand
    -0.60
     henvisninger
    -0.59
     gyhoeddwyd
    -0.59
    Enllaces
    -0.59
    vät
    -0.59
    POSITIVE LOGITS
     Sigma
    0.98
    Sigma
    0.89
     CYTHON
    0.78
    AxisAlignment
    0.75
     butts
    0.67
    gnore
    0.67
     Rond
    0.66
     Pneumonia
    0.65
     kres
    0.64
     JSTOR
    0.64
    Activations Density 0.001%

    No Known Activations