© 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. 15340
    Prev
    Next
    INDEX
    Explanations

    references to specific high-priority healthcare or safety monitoring facilities

    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
    ji
    -0.52
    FormTagHelper
    -0.52
     Signalez
    -0.51
    basa
    -0.50
    ality
    -0.50
    ėj
    -0.50
    keit
    -0.49
    forall
    -0.49
     oignons
    -0.48
    ьем
    -0.47
    POSITIVE LOGITS
    HS
    2.31
     HS
    0.98
     HSBC
    0.81
     Италијани
    0.79
     betweenstory
    0.77
     متعلقه
    0.74
    
    0.65
    wpi
    0.64
    ętr
    0.63
     initComponents
    0.63
    Activations Density 0.001%

    No Known Activations