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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13830
    Prev
    Next
    INDEX
    Explanations

    instructions related to database querying and data manipulation

    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
    GraphicsUnit
    -0.67
     estekak
    -0.64
    +#+
    -0.60
    SCHE
    -0.55
    jsonwebtoken
    -0.55
     Ades
    -0.53
    NewGuid
    -0.52
    ERTY
    -0.52
    __]
    -0.51
    viembre
    -0.50
    POSITIVE LOGITS
    bili
    2.67
    abili
    2.36
     bili
    2.28
     Bili
    1.80
    ibili
    1.10
    tabili
    0.98
    labili
    0.85
    били
    0.83
    ili
    0.68
    存于互联网档案馆
    0.64
    Activations Density 0.001%

    No Known Activations