© 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. 13936
    Prev
    Next
    INDEX
    Explanations

    references to the process of establishing or measuring the level or accuracy of some parameter

    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
    sizeCache
    -0.68
    CreateMap
    -0.58
    муж
    -0.57
    PopupMenu
    -0.57
    PROLOG
    -0.57
     Treff
    -0.56
    %\\
    -0.55
    WithIOException
    -0.55
    matchCondition
    -0.54
    ANTLR
    -0.54
    POSITIVE LOGITS
     InputDecoration
    0.59
    存于互联网档案馆
    0.57
    ceus
    0.56
    Health
    0.55
    揄
    0.52
    lète
    0.50
    atisme
    0.50
     تضيفلها
    0.50
     ioe
    0.50
    ohol
    0.50
    Activations Density 0.022%

    No Known Activations