© 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. 1639
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with governmental or political wrong-doing

    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
    principalTable
    -0.83
     MonoBehaviour
    -0.77
    $_['
    -0.69
     jsPsych
    -0.66
     ostavi
    -0.63
    feitura
    -0.59
    phite
    -0.57
     AssemblyCulture
    -0.57
    InjectAttribute
    -0.57
    styleType
    -0.57
    POSITIVE LOGITS
     intelligence
    1.15
     CIA
    1.04
    intelligence
    0.95
     Intelligence
    0.93
    Intelligence
    0.92
    CIA
    0.91
     spy
    0.89
     intel
    0.88
     NSA
    0.86
     secret
    0.84
    Activations Density 1.133%

    No Known Activations