© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15243
    Prev
    Next
    INDEX
    Explanations

    features related to the cumulative effect or total measurement of a variable

    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
     cum
    -2.77
    cum
    -2.48
     Cum
    -2.38
    Cum
    -2.33
    CUM
    -1.78
     CUM
    -1.74
     متعلقه
    -0.94
    GraphicsUnit
    -0.91
    tagHelperRunner
    -0.91
     kum
    -0.85
    POSITIVE LOGITS
     cumulative
    1.34
    cumulative
    0.74
     Cumulative
    0.67
     مس
    0.50
    Cumulative
    0.49
     >=",
    0.47
    ##
    0.46
     volume
    0.46
    拍
    0.46
     đ
    0.44
    Activations Density 0.001%

    No Known Activations