© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4660
    Prev
    Next
    INDEX
    Explanations

    references to database operations or queries

    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
    huriyet
    -0.64
    isand
    -0.63
     Judith
    -0.62
     Parcelable
    -0.60
    ंदीखरीदारी
    -0.57
     Cabot
    -0.57
    ,:);
    -0.56
    gdx
    -0.55
    moed
    -0.55
    urlaub
    -0.55
    POSITIVE LOGITS
    db
    3.06
     db
    3.05
    DB
    2.70
     DB
    2.58
    Db
    2.25
     Db
    2.08
     database
    1.75
     Database
    1.71
    数据库
    1.69
    Database
    1.60
    Activations Density 0.025%

    No Known Activations