© 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. 6218
    Prev
    Next
    INDEX
    Explanations

    questions related to identifying who or which

    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
     that
    -0.52
     unusually
    -0.49
     Tân
    -0.48
     consideration
    -0.47
    getMock
    -0.47
     Stuhl
    -0.47
     although
    -0.47
    ällt
    -0.47
     huge
    -0.47
    vater
    -0.47
    POSITIVE LOGITS
     Which
    1.02
    Which
    0.97
    InputBorder
    0.90
    IsContent
    0.88
     Whence
    0.83
    哪个
    0.83
    ScopeManager
    0.82
    RectangleBorder
    0.81
     Whose
    0.79
    Whose
    0.78
    Activations Density 0.190%

    No Known Activations