© 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. 15142
    Prev
    Next
    INDEX
    Explanations

    references to the word "Even," indicating the neuron is detecting instances of the word "Even."

    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
    脚注の使い方
    -0.87
    IntoConstraints
    -0.87
     kaarangay
    -0.85
     وتسجيلات
    -0.85
    XmlAccessType
    -0.79
     linkovi
    -0.79
    ViewFeatures
    -0.79
    enumi
    -0.77
     bezeichneter
    -0.77
     Савезне
    -0.75
    POSITIVE LOGITS
     Even
    1.25
    Even
    1.10
     EVEN
    0.63
    EVEN
    0.59
     Même
    0.57
    Даже
    0.57
     Даже
    0.53
    teen
    0.52
    смотря
    0.49
     hộp
    0.49
    Activations Density 0.006%

    No Known Activations