© 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. 26950
    Prev
    Next
    INDEX
    Explanations

    references to various types of "pot" or "potent" materials, particularly in relation to drugs or cooking

    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
    Referències
    -0.83
    chenkt
    -0.82
    nastics
    -0.80
    CloseOperation
    -0.79
    plink
    -0.78
     Вікіпе
    -0.77
     }}"></
    -0.75
    etheless
    -0.73
    setVerticalGroup
    -0.73
     McLeod
    -0.70
    POSITIVE LOGITS
     Pot
    1.59
    pot
    1.56
     POT
    1.55
     pot
    1.50
    Pot
    1.48
    POT
    1.47
     Potts
    1.41
     pots
    1.36
     Pots
    1.21
     Potter
    1.17
    Activations Density 0.008%

    No Known Activations