© 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. 2-RES-MATRYOSHKA-DC
    7. 2927
    Prev
    Next
    INDEX
    Explanations

    references to the gene "gi" or the term "gi" itself

    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
    onActivityResult
    -0.65
     Santi
    -0.64
    basicConfig
    -0.64
    quisa
    -0.64
     Farb
    -0.63
     Feynman
    -0.62
     fémin
    -0.62
     politiet
    -0.62
    RTEE
    -0.62
     Samaria
    -0.61
    POSITIVE LOGITS
    gi
    3.06
    GI
    2.53
    Gi
    2.31
     Gi
    2.28
     gi
    2.23
    gy
    2.14
     GI
    1.98
    GY
    1.75
    gia
    1.63
     Gy
    1.48
    Activations Density 0.076%

    No Known Activations