© 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. 3731
    Prev
    Next
    INDEX
    Explanations

    references to a specific identifier or label

    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
     فريبيس
    -0.61
     externi
    -0.53
     McP
    -0.53
    لاب
    -0.52
    bre
    -0.51
    illance
    -0.50
    GeneratedMessage
    -0.50
    Brun
    -0.50
     wikipagina
    -0.49
    herjee
    -0.49
    POSITIVE LOGITS
    ba
    3.28
    Ba
    2.83
    BA
    2.81
     Ba
    2.80
     ba
    2.70
     BA
    2.47
     BAH
    1.56
    baa
    1.52
     BAI
    1.48
    BAH
    1.41
    Activations Density 0.043%

    No Known Activations