© 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. 3-RES-MATRYOSHKA-DC
    7. 3379
    Prev
    Next
    INDEX
    Explanations

    code blocks, specifically those related to SQL

    oai_token-act-pair · gemini-2.0-flash
    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
    rimin
    -0.52
    impin
    -0.51
    fiez
    -0.49
    Trimethyl
    -0.49
    زیین
    -0.47
    joje
    -0.45
    ainville
    -0.45
     dung
    -0.45
     ground
    -0.44
     Verbrauch
    -0.44
    POSITIVE LOGITS
    ArgsConstructor
    0.91
     propOrder
    0.80
    KommentareTeilen
    0.79
    AddTagHelper
    0.78
     createSlice
    0.76
    StoryboardSegue
    0.75
    \{\\
    0.68
    AnchorStyles
    0.68
    Personensuche
    0.68
    NavController
    0.66
    Activations Density 0.896%

    No Known Activations