© 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. 13930
    Prev
    Next
    INDEX
    Explanations

    the phrase "not" or "not just" that indicates negation or emphasis on exclusion

    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
     Theſe
    -1.05
     Efq
    -1.01
     Anſ
    -0.94
     BoxFit
    -0.91
    ſelves
    -0.89
     öffnungszeiten
    -0.86
     ―――――
    -0.86
     preſent
    -0.83
     ainfi
    -0.83
    ^(@)
    -0.82
    POSITIVE LOGITS
     (
    0.73
     
    0.66
    <eos>
    0.62
     a
    0.58
    ,
    0.55
     of
    0.54
    ↵
    0.54
    beginPath
    0.52
     "
    0.51
    ↵↵
    0.51
    Activations Density 0.271%

    No Known Activations