© 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. 1-RES-MATRYOSHKA-DC
    7. 1195
    Prev
    Next
    INDEX
    Explanations

    references to gases or gas-related formulations involved in chemical processes

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Bridget
    -0.57
    mailer
    -0.52
     Wolver
    -0.51
     Бере
    -0.51
     Kür
    -0.50
     armature
    -0.49
    截
    -0.48
     bounding
    -0.47
     téléphonique
    -0.47
    Бере
    -0.47
    POSITIVE LOGITS
     gas
    4.94
     Gas
    4.44
    Gas
    4.31
    gas
    4.06
     GAS
    3.69
    GAS
    3.39
     gases
    2.89
     gás
    2.78
    ガス
    2.50
     газо
    2.41
    Activations Density 0.065%

    No Known Activations