© 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. 18058
    Prev
    Next
    INDEX
    Explanations

    financial transactions and consultancy agreements related to healthcare and pharmaceutical companies

    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
    RegistryLite
    -0.60
     '
    -0.52
     Trust
    -0.47
    izien
    -0.46
    tuned
    -0.46
     ''
    -0.46
     «
    -0.46
    Lie
    -0.46
    بالإنجليزية
    -0.45
    出版年
    -0.45
    POSITIVE LOGITS
    aarrggbb
    0.76
    parsedMessage
    0.76
     ProtoMessage
    0.65
    AsUp
    0.64
    vartis
    0.64
     CWE
    0.63
     myſelf
    0.61
    uxxxx
    0.60
    expandindo
    0.60
    WriteAttribute
    0.60
    Activations Density 0.016%

    No Known Activations