© 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. 3-RES-MATRYOSHKA-DC
    7. 1636
    Prev
    Next
    INDEX
    Explanations

    the word "even"

    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
    Not in Any Lists

    No Comments

    Negative Logits
    protoimpl
    -0.90
     незавершена
    -0.80
    LayoutPanel
    -0.79
    RTLD
    -0.79
    oneofs
    -0.76
    parsedMessage
    -0.73
    mbggenerated
    -0.73
    lapsingToolbar
    -0.71
     ProtoMessage
    -0.71
    PhysRevD
    -0.69
    POSITIVE LOGITS
     even
    3.55
    even
    3.27
    Even
    3.00
     Even
    2.94
     EVEN
    2.86
    EVEN
    2.55
     incluso
    2.25
    Даже
    2.25
     даже
    2.23
     Incluso
    2.20
    Activations Density 0.248%

    No Known Activations