© 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. 25868
    Prev
    Next
    INDEX
    Explanations

    phrases expressing support and loyalty to a leader

    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
    tagHelperRunner
    -0.66
    ViewFeatures
    -0.65
    ValueStyle
    -0.59
     twain
    -0.57
    WebVitals
    -0.56
    riwal
    -0.56
     yah
    -0.55
     Anſ
    -0.55
    downs
    -0.55
     impact
    -0.54
    POSITIVE LOGITS
    sidemargin
    0.62
    ArgsConstructor
    0.57
     alugar
    0.52
     brothers
    0.52
    #
    0.50
    lorus
    0.50
    Stain
    0.49
    myra
    0.49
     Rosenberg
    0.48
     halved
    0.47
    Activations Density 0.044%

    No Known Activations