© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 14174
    Prev
    Next
    INDEX
    Explanations

    the concept of identifying or excluding specific key terms, particularly the term "exclude."

    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
     exclusion
    -0.77
    exclusion
    -0.76
     Exclusion
    -0.73
    FormTagHelper
    -0.62
    MigrationBuilder
    -0.58
    Present
    -0.56
    LIBRA
    -0.56
    Ilustra
    -0.56
    illion
    -0.54
    vised
    -0.53
    POSITIVE LOGITS
     exclude
    1.83
     Exclude
    1.10
    exclude
    1.02
     excludes
    0.91
    Exclude
    0.82
    Reflect
    0.56
     invokingState
    0.56
    UseVisualStyle
    0.55
     Reflect
    0.54
    liminary
    0.53
    Activations Density 0.002%

    No Known Activations