© 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. 7395
    Prev
    Next
    INDEX
    Explanations

    instructions related to creating or defining database tables

    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
    SELECT
    -0.71
    cinnati
    -0.63
     SELECT
    -0.59
    URUS
    -0.56
     humain
    -0.56
    select
    -0.49
     reac
    -0.49
    COLUMNS
    -0.48
    Oracle
    -0.47
    Databases
    -0.47
    POSITIVE LOGITS
    DockStyle
    0.79
     חיצוניים
    0.77
     transfieras
    0.75
    }{*}{
    0.74
     CanadaChoose
    0.72
    jsxFileName
    0.72
    ImageContext
    0.69
    AndEndTag
    0.69
    AndroidJUnit
    0.66
    estacks
    0.64
    Activations Density 0.104%

    No Known Activations