© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 3532
    Prev
    Next
    INDEX
    Explanations

    references to database creation and management commands

    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
    ñana
    -0.59
    abetes
    -0.55
    aarrggbb
    -0.55
    شهاد
    -0.54
     Jib
    -0.53
     Menschheit
    -0.52
     cakes
    -0.48
    saraba
    -0.47
     Suk
    -0.47
    świad
    -0.46
    POSITIVE LOGITS
     database
    2.97
     Database
    2.72
     databases
    2.61
    database
    2.53
    Database
    2.41
     Databases
    2.41
     DATABASE
    2.30
    数据库
    2.00
    databases
    1.90
    DATABASE
    1.89
    Activations Density 0.024%

    No Known Activations