© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 382
    Prev
    Next
    INDEX
    Explanations

    legal terms and regulations related to employment discrimination and rights

    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
     intptr
    -0.69
     
    -0.59
     bad
    -0.58
     bigger
    -0.58
     almost
    -0.56
    𝙫
    -0.56
     dodgy
    -0.53
    bad
    -0.53
     hugely
    -0.52
    ط
    -0.52
    POSITIVE LOGITS
     étoient
    0.91
     fubject
    0.91
     feroit
    0.85
     avoient
    0.84
     uſe
    0.83
     ſtate
    0.82
     prêtres
    0.81
     hereinafter
    0.80
     perfons
    0.80
     pleaſure
    0.79
    Activations Density 2.667%

    No Known Activations