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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 24586
    Prev
    Next
    INDEX
    Explanations

    mentions of Arab individuals or groups

    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
    Montana
    -0.76
    anthene
    -0.75
     fileName
    -0.73
     Montana
    -0.68
    fileName
    -0.67
    allowNull
    -0.66
    queles
    -0.62
    jshint
    -0.62
     FormControl
    -0.60
    ਹੀ
    -0.57
    POSITIVE LOGITS
     Arabs
    1.44
     ARAB
    1.34
    ARAB
    1.27
     Arab
    1.27
     arab
    1.26
    idopsis
    1.24
    Arab
    1.23
     Ara
    1.15
    Ara
    1.15
     Lucas
    1.03
    Activations Density 0.009%

    No Known Activations