Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14217
    Prev
    Next
    INDEX
    Explanations

    instances where the model perceives something as confusing or ambiguous

    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
     autorytatywna
    -0.81
     Normdatei
    -0.80
     lenker
    -0.72
     للمعارف
    -0.61
     sako
    -0.57
    Дереккөздер
    -0.57
     compromis
    -0.56
     zuk
    -0.56
    قایناق‌لار
    -0.56
    γου
    -0.55
    POSITIVE LOGITS
     confusing
    2.13
     confuse
    0.97
     confuses
    0.92
    enumii
    0.64
     BufferedReader
    0.57
     stringBy
    0.56
     annoying
    0.54
     distracting
    0.54
     boring
    0.54
    DataSnapshot
    0.54
    Activations Density 0.000%

    No Known Activations