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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5580
    Prev
    Next
    INDEX
    Explanations

    references to human beings

    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
     referenties
    -0.72
     Vertigo
    -0.61
     preponderance
    -0.57
    Пример
    -0.56
     препратки
    -0.55
     inception
    -0.54
     whereof
    -0.54
     Drexel
    -0.54
     fria
    -0.53
     Hustle
    -0.52
    POSITIVE LOGITS
     human
    1.52
    human
    1.33
     HUMAN
    1.22
    Human
    1.16
    HUMAN
    1.16
     Human
    1.11
     humano
    1.09
     humain
    1.02
     humanity
    1.02
     humans
    0.93
    Activations Density 0.066%

    No Known Activations