© 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. 1-RES-MATRYOSHKA-DC
    7. 214
    Prev
    Next
    INDEX
    Explanations

    sequences of characters that resemble structured code, labels, or identifiers, often including specific acronyms or patterns associated with technical 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
    VIAF
    -0.68
     Efq
    -0.67
     soeur
    -0.66
     oeufs
    -0.66
     avoient
    -0.65
     gomma
    -0.65
     debout
    -0.63
     disant
    -0.63
     vieill
    -0.62
     îna
    -0.62
    POSITIVE LOGITS
    CR
    1.11
     CR
    1.09
     CC
    1.09
     CTC
    1.04
    CRC
    1.02
     Cl
    1.02
     cr
    1.02
     CCR
    1.01
     Cr
    0.98
     CL
    0.98
    Activations Density 4.777%

    No Known Activations