© 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. 0-RES-MATRYOSHKA-DC
    7. 12101
    Prev
    Next
    INDEX
    Explanations

    references to specific structured elements, mainly focusing on detailed technical or mathematical terminology

    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
    lia
    -0.83
     للمعارف
    -0.66
    LIA
    -0.66
     nakalista
    -0.65
     vastaan
    -0.60
     iprot
    -0.59
    Quiénes
    -0.58
    engeance
    -0.57
    rillation
    -0.56
    lias
    -0.56
    POSITIVE LOGITS
    dia
    2.28
    diya
    0.99
    DIA
    0.68
    kháu
    0.63
    lotto
    0.55
    dias
    0.54
    )});
    0.54
    ropra
    0.50
    Indian
    0.48
     Indian
    0.47
    Activations Density 0.001%

    No Known Activations