© 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. 22-RES-MATRYOSHKA-DC
    7. 3027
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "rules" or similar concepts involving workplace safety and declarations of defiance

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     resourceCulture
    -0.66
     anzunehmen
    -0.62
    memoized
    -0.60
    complexContent
    -0.59
    thâu
    -0.59
    WriteTagHelper
    -0.59
    IndentedString
    -0.58
    dataclass
    -0.58
     Recher
    -0.57
    featureID
    -0.56
    POSITIVE LOGITS
     violation
    2.25
     violate
    2.03
     violations
    2.02
     violating
    2.00
     violated
    1.91
     Violation
    1.88
     violates
    1.84
    violation
    1.80
    viol
    1.78
     compliance
    1.75
    Activations Density 0.678%

    No Known Activations