© 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. 9294
    Prev
    Next
    INDEX
    Explanations

    references to infrastructure

    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
     argint
    -0.86
     Boud
    -0.80
     Judson
    -0.79
     judiciaire
    -0.78
     Jocelyn
    -0.78
     oiseaux
    -0.78
     Elias
    -0.77
     Bals
    -0.77
     Hoyt
    -0.77
     Acha
    -0.76
    POSITIVE LOGITS
     infrastructure
    1.59
     Infrastructure
    1.50
     infrastructures
    1.48
     infra
    1.44
    infrastructure
    1.40
     Infra
    1.31
    Infrastructure
    1.30
    Infra
    1.23
    infra
    1.20
    frastructure
    1.11
    Activations Density 0.003%

    No Known Activations