© 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. 3457
    Prev
    Next
    INDEX
    Explanations

    references to passages or sections in text

    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
     متعلقه
    -0.95
     Paglinawan
    -0.91
     Signalez
    -0.87
     Infórmanos
    -0.79
     Monfieur
    -0.78
     Савезне
    -0.77
     AspNetCore
    -0.76
     myſelf
    -0.75
    ագրություններ
    -0.73
     تانيه
    -0.72
    POSITIVE LOGITS
     passage
    3.22
    passage
    2.69
     passages
    2.67
     Passage
    2.64
    Passage
    2.55
     pasaje
    1.52
     passagem
    1.22
     passaggio
    1.15
    assage
    0.91
     excerpt
    0.82
    Activations Density 0.004%

    No Known Activations