© 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. 15284
    Prev
    Next
    INDEX
    Explanations

    references to mortality or death, particularly highlighting the concept of being mortal

    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
     Reine
    -0.62
     Sert
    -0.58
     Процитовано
    -0.56
    Примітки
    -0.54
    WEBPACK
    -0.54
     Reverso
    -0.53
     Rowling
    -0.53
     senescence
    -0.52
    DoubleQuotes
    -0.52
     BoxDecoration
    -0.52
    POSITIVE LOGITS
     mortal
    2.14
     Mortal
    1.93
    mortal
    1.50
    Mortal
    1.46
     mortals
    1.06
     ah
    0.82
     Proceedings
    0.82
     earthly
    0.73
    Proceedings
    0.68
    Datuak
    0.63
    Activations Density 0.002%

    No Known Activations