© 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. 2-RES-MATRYOSHKA-DC
    7. 2411
    Prev
    Next
    INDEX
    Explanations

    mentions of the name or abbreviation "Bal" or "bales," likely referring to the concept of bales or related to "balers."

    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
    Negative Logits
    SequentialGroup
    -0.70
    WriteAttribute
    -0.65
    Jeografia
    -0.65
    addPreferredGap
    -0.64
    esez
    -0.64
    ramienta
    -0.64
    parency
    -0.63
    ѓ
    -0.62
    CPC
    -0.61
    kuper
    -0.61
    POSITIVE LOGITS
     Bal
    3.52
    Bal
    3.42
     bal
    2.95
     BAL
    2.86
    bal
    2.78
    BAL
    2.77
     Бал
    1.70
    balan
    1.59
    Balan
    1.55
     balancer
    1.55
    Activations Density 0.011%

    No Known Activations