© 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. 6838
    Prev
    Next
    INDEX
    Explanations

    terms related to exemptions and regulatory relief

    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
     Administrativna
    -0.57
     Signalez
    -0.54
    StructEnd
    -0.53
    neté
    -0.53
     fevere
    -0.53
    AutoScaleMode
    -0.52
     chastity
    -0.52
    Required
    -0.49
     disponibilités
    -0.49
    REQUIRED
    -0.49
    POSITIVE LOGITS
     exemption
    0.77
     exemptions
    0.71
     relaxation
    0.69
    Portály
    0.68
     Exemption
    0.67
     granted
    0.66
     lenient
    0.66
     amnesty
    0.65
     special
    0.64
     granting
    0.63
    Activations Density 1.052%

    No Known Activations