© 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. 14023
    Prev
    Next
    INDEX
    Explanations

    references to specific citation labels or identifiers

    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
     ComVisible
    -0.86
    FunctionFlags
    -0.71
    اریخ
    -0.63
    TagMode
    -0.63
     autorytatywna
    -0.61
     onCreateView
    -0.60
    DockStyle
    -0.59
     chi̍t
    -0.58
    Somewhere
    -0.54
     referenties
    -0.54
    POSITIVE LOGITS
    cagon
    1.32
     unacceptable
    0.92
    AGCT
    0.90
     Robin
    0.77
    anta
    0.74
    Robin
    0.74
     aryl
    0.71
     summar
    0.71
     Roma
    0.71
     상세
    0.70
    Activations Density 0.028%

    No Known Activations