© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15830
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "misunderstood" or its variants

    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
    CopyWith
    -0.69
    httphttps
    -0.57
     bağlantılar
    -0.56
    jedis
    -0.54
    katalog
    -0.54
     NSCoder
    -0.54
    loze
    -0.52
    مراجع
    -0.52
    DOCT
    -0.50
     dobla
    -0.50
    POSITIVE LOGITS
     misunder
    2.88
     misunderstood
    2.67
     misunderstand
    2.63
     misconception
    1.66
     misinterpreted
    1.60
     misconceptions
    1.55
     mistaken
    1.45
    误会
    1.38
     misread
    1.09
     miscon
    0.88
    Activations Density 0.002%

    No Known Activations