© 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. 6973
    Prev
    Next
    INDEX
    Explanations

    references to individuals or instances

    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
    Individual
    -0.92
     individual
    -0.90
     Individual
    -0.85
    individual
    -0.84
     individually
    -0.67
    個別
    -0.62
     individuales
    -0.60
     индивидуаль
    -0.56
     Taran
    -0.56
    oooooooooooooooo
    -0.55
    POSITIVE LOGITS
     individuals
    1.89
     Individuals
    1.84
    Individuals
    1.83
    individuals
    1.66
     individus
    1.38
     individuos
    1.28
     indivíduos
    1.28
     persons
    1.06
     Persons
    0.93
    persons
    0.85
    Activations Density 0.013%

    No Known Activations