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. 12-RES-MATRYOSHKA-DC
    4. 11179
    Prev
    Next
    INDEX
    Explanations

    concepts related to entropy and its mathematical properties

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     testGet
    -0.60
     Gué
    -0.58
     Schulte
    -0.57
     ReactDOM
    -0.56
    Rod
    -0.56
     aspar
    -0.56
    initWith
    -0.56
    adə
    -0.56
    ål
    -0.55
    érience
    -0.55
    POSITIVE LOGITS
     entropy
    1.80
     Entropy
    1.65
    entropy
    1.60
    Entropy
    1.55
    熵
    1.03
     rappel
    0.91
     '\\;'
    0.78
    blurRadius
    0.78
    OrderInfo
    0.77
    Gesellschaft
    0.76
    Activations Density 0.007%

    No Known Activations