© 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. 20620
    Prev
    Next
    INDEX
    Explanations

    references to military conflicts and the policies surrounding them, particularly related to George W. Bush's administration

    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
     Siva
    -0.66
     banyo
    -0.60
    гант
    -0.54
     threatening
    -0.50
     Frederic
    -0.50
     Benfica
    -0.49
     raider
    -0.49
     thine
    -0.48
    gın
    -0.48
    tahui
    -0.47
    POSITIVE LOGITS
     ujednoznacz
    0.88
    Jeografia
    0.70
    帖最后由
    0.60
     EClass
    0.59
    fjspx
    0.59
     Biôgrafia
    0.59
     كومونز
    0.58
    يديا
    0.57
    География
    0.56
     globe
    0.54
    Activations Density 0.062%

    No Known Activations