© 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. 9253
    Prev
    Next
    INDEX
    Explanations

    the presence of the name "Don" along with variations of its capitalization

    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
     Myers
    -0.87
    alignItems
    -0.82
    ]`
    -0.80
    setVerticalGroup
    -0.75
    Peacock
    -0.75
     Heine
    -0.74
    BASEPATH
    -0.73
    Especificações
    -0.72
     թվական
    -0.71
     alignItems
    -0.71
    POSITIVE LOGITS
     Donny
    1.29
     DON
    1.16
    Don
    1.13
     Don
    1.12
     Donat
    1.08
     Dons
    1.03
    don
    1.02
     Donnelly
    1.02
    Dono
    1.00
    DON
    0.98
    Activations Density 0.022%

    No Known Activations