© 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
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 13951
    Prev
    Next
    INDEX
    Explanations

    references to chemical compound data related to molecular structures and properties

    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
     ProtoMessage
    -0.90
    adaptiveStyles
    -0.86
    脚注の使い方
    -0.81
    BufferException
    -0.81
    MessageTagHelper
    -0.80
    ftagPool
    -0.79
    PageRoute
    -0.79
    发表于
    -0.77
     GenerationType
    -0.77
    WindowConstants
    -0.75
    POSITIVE LOGITS
     EA
    2.08
    EA
    1.81
     heap
    0.81
     lump
    0.78
     Lump
    0.76
     ea
    0.71
    lump
    0.60
    heap
    0.60
     heaps
    0.59
    Ea
    0.52
    Activations Density 0.003%

    No Known Activations