© 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. 2831
    Prev
    Next
    INDEX
    Explanations

    references to specific data fields or identifiers in the document

    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
    deter
    -0.55
    гро
    -0.51
     Capo
    -0.51
    Cama
    -0.49
     tull
    -0.48
    roupa
    -0.47
    codable
    -0.47
    ello
    -0.46
    Sov
    -0.45
    erover
    -0.45
    POSITIVE LOGITS
     PD
    2.98
    PD
    2.94
    pd
    2.16
     pd
    2.08
     Pd
    1.36
    Pd
    1.35
     PDG
    1.34
     PDI
    1.17
    PDS
    1.09
     PDS
    1.07
    Activations Density 0.038%

    No Known Activations