© 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. 26210
    Prev
    Next
    INDEX
    Explanations

    mentions of disability claims and associated administrative decisions

    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
    ndham
    -0.55
    esper
    -0.49
    oyd
    -0.48
     Fan
    -0.46
     fan
    -0.44
    ballon
    -0.43
    rén
    -0.43
    łgorzata
    -0.43
    archiviato
    -0.42
    vited
    -0.42
    POSITIVE LOGITS
     contextLoads
    0.76
    PerformLayout
    0.60
    ⓧ
    0.59
    MigrationBuilder
    0.58
    onset
    0.56
     propOrder
    0.56
    Personensuche
    0.55
     kaarangay
    0.55
    Cyfarwyddwr
    0.55
     hemi
    0.54
    Activations Density 0.035%

    No Known Activations