© 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. 13479
    Prev
    Next
    INDEX
    Explanations

    mentions of females in scientific data

    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
    TagMode
    -0.88
    tagHelperRunner
    -0.86
     humans
    -0.82
    ImageContext
    -0.75
     Humans
    -0.73
    Humans
    -0.73
    humans
    -0.69
    ibos
    -0.65
    userdetails
    -0.64
    copg
    -0.64
    POSITIVE LOGITS
     females
    1.65
     Females
    1.37
    Females
    1.13
     males
    0.66
     Males
    0.58
    Males
    0.55
    fem
    0.49
     générale
    0.46
     Mendel
    0.44
    backtracking
    0.43
    Activations Density 0.002%

    No Known Activations