© 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. 17969
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and financial contexts

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -0.81
     faſt
    -0.77
     whoſe
    -0.74
     Jefus
    -0.70
     houſe
    -0.70
     purpoſe
    -0.70
     fhew
    -0.69
     Monfieur
    -0.69
     whofe
    -0.69
     itſelf
    -0.67
    POSITIVE LOGITS
    ArgumentParser
    0.62
     disponibilités
    0.59
    oredCriteria
    0.55
    StructEnd
    0.50
    queryInterface
    0.50
     ISNI
    0.47
    MemoryWarning
    0.45
    EndContext
    0.45
    گری
    0.45
     <<<<<<<<<<<<<<
    0.44
    Activations Density 0.078%

    No Known Activations