© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-RES-MATRYOSHKA-DC
    7. 1057
    Prev
    Next
    INDEX
    Explanations

    references to children or youth

    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
     investors
    -0.65
     uomini
    -0.58
     Advisors
    -0.58
     voters
    -0.55
     Investors
    -0.55
    investors
    -0.54
    Investors
    -0.53
     advisors
    -0.52
    DriverManager
    -0.51
     Holders
    -0.51
    POSITIVE LOGITS
     children
    3.69
     child
    3.67
     Children
    3.36
    Children
    3.34
     Child
    3.27
    Child
    3.25
    children
    3.25
    child
    3.20
     CHILDREN
    3.05
     CHILD
    3.03
    Activations Density 1.034%

    No Known Activations