© 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. 23590
    Prev
    Next
    INDEX
    Explanations

    references to minority groups and their representation

    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
     secondaire
    -0.61
     autorytatywna
    -0.59
     الاطلاع
    -0.59
    ogly
    -0.57
    Kamu
    -0.57
     Kamu
    -0.56
    bleau
    -0.54
     Efq
    -0.53
    Javadoc
    -0.53
    ]")]
    -0.53
    POSITIVE LOGITS
    GEBURTSDATUM
    0.75
    IntoConstraints
    0.63
    AndroidJUnit
    0.52
    QMetaType
    0.48
     HttpNotFound
    0.48
     medži
    0.46
    WriteTagHelper
    0.46
    aged
    0.44
    Durata
    0.44
     Exacts
    0.43
    Activations Density 0.437%

    No Known Activations