© 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. 32455
    Prev
    Next
    INDEX
    Explanations

    terms related to foundations and organizations

    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
     Virol
    -0.88
     étoient
    -0.84
     Bengals
    -0.83
     Anſ
    -0.81
    RSpec
    -0.80
     Marisa
    -0.80
     végétale
    -0.79
     uſed
    -0.78
    extAlignment
    -0.77
    styleUrls
    -0.76
    POSITIVE LOGITS
     Foundation
    1.66
     foundation
    1.59
    Foundations
    1.59
    Foundation
    1.57
     foundations
    1.54
    foundation
    1.52
     FOUNDATION
    1.52
     Foundations
    1.48
     fondation
    1.11
     Fondation
    1.10
    Activations Density 0.010%

    No Known Activations