Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-RES-MATRYOSHKA-DC
    4. 30198
    Prev
    Next
    INDEX
    Explanations

    the word "metric" in mathematical or scientific contexts

    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
    المكان
    -0.77
    databind
    -0.71
    setupUi
    -0.70
    Распо
    -0.70
     Unwin
    -0.69
    baomidou
    -0.68
    ILayout
    -0.66
    Unmarshal
    -0.66
     corrispond
    -0.65
     dignité
    -0.65
    POSITIVE LOGITS
     metric
    1.30
     metrics
    1.30
    Metrics
    1.26
    Metric
    1.23
     Metrics
    1.20
     Metric
    1.18
    metrics
    1.00
    metric
    0.94
     METER
    0.83
    指标
    0.80
    Activations Density 0.003%

    No Known Activations