© 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. 1348
    Prev
    Next
    INDEX
    Explanations

    mentions of people and the word 'he' and dates

    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
     weren
    -0.59
     necesitaba
    -0.55
    webElementXpaths
    -0.53
     consisted
    -0.52
     lenker
    -0.50
    scriptcase
    -0.50
    mybatisplus
    -0.49
     mógł
    -0.49
    bcryptjs
    -0.48
     bánh
    -0.47
    POSITIVE LOGITS
     served
    0.96
     authored
    0.96
    served
    0.85
     founded
    0.80
     Served
    0.79
     taught
    0.77
     studied
    0.72
    Served
    0.71
     worked
    0.70
     co
    0.67
    Activations Density 0.689%

    No Known Activations