© 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. 3441
    Prev
    Next
    INDEX
    Explanations

    references to specific genomics databases and related resources

    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
     com
    -0.90
     Com
    -0.80
    Com
    -0.79
     COM
    -0.71
    rizona
    -0.71
    html
    -0.67
     html
    -0.67
    COM
    -0.65
    fxml
    -0.63
    coms
    -0.63
    POSITIVE LOGITS
     CreateTagHelper
    0.98
     onOptions
    0.74
    RefNanny
    0.69
     ostavi
    0.67
    AutoField
    0.66
    󠁣
    0.64
    Билгалдахарш
    0.63
    ISupport
    0.60
    MessageTagHelper
    0.59
    ContextHolder
    0.59
    Activations Density 0.075%

    No Known Activations