© 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. 24-RES-MATRYOSHKA-DC
    7. 1364
    Prev
    Next
    INDEX
    Explanations

    words related to US politics

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.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.24.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     AssemblyTitle
    -0.67
    AutoScale
    -0.63
    bindParam
    -0.62
    GraphicsUnit
    -0.57
    enderror
    -0.54
     royaume
    -0.52
     forState
    -0.52
    ICHT
    -0.51
     linkovi
    -0.51
     perifer
    -0.50
    POSITIVE LOGITS
     House
    1.03
     bill
    0.99
     committee
    0.97
     passed
    0.95
     Committee
    0.93
     Senate
    0.91
     passage
    0.88
    Committee
    0.84
    House
    0.84
     bills
    0.83
    Activations Density 0.697%

    No Known Activations