© 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
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 15622
    Prev
    Next
    INDEX
    Explanations

    references to human biology or studies involving humans

    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
     Gump
    -0.66
     estekak
    -0.63
    kháu
    -0.59
    شهاد
    -0.55
    COUVER
    -0.54
     disambiguazione
    -0.52
    ValueStyle
    -0.52
    הערות
    -0.51
    {}{}
    -0.50
    ⓧ
    -0.50
    POSITIVE LOGITS
    human
    1.38
     humanitarian
    1.30
     inhuman
    1.08
     Humanitarian
    1.05
    hum
    0.97
    itarian
    0.90
     humanity
    0.88
     Humanity
    0.81
     humanities
    0.80
     Humanities
    0.75
    Activations Density 0.008%

    No Known Activations