© 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. 15230
    Prev
    Next
    INDEX
    Explanations

    mentions of specific chemical inhibitors

    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
     inhibitor
    -0.69
    /*
    -0.63
     noDo
    -0.58
     betweenstory
    -0.56
    Suara
    -0.55
    Twas
    -0.51
     gehouden
    -0.51
    都说
    -0.50
     adhesivo
    -0.49
    quelize
    -0.49
    POSITIVE LOGITS
     inhibitors
    1.63
     Inhibitors
    1.13
    expandindo
    0.63
    EDEFAULT
    0.63
    AndEndTag
    0.62
     disponibilités
    0.59
     Roskov
    0.59
    schedulers
    0.56
     متعلقه
    0.55
     gyhoeddwyd
    0.54
    Activations Density 0.001%

    No Known Activations