© 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. 6445
    Prev
    Next
    INDEX
    Explanations

    references to specific components made of rubber or beads, particularly in contexts related to materials or scientific analyses

    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
     Jaff
    -0.73
    endphp
    -0.72
     McMillan
    -0.66
     Bronson
    -0.66
     Hugo
    -0.66
     Monroe
    -0.65
     Steele
    -0.65
     tubeless
    -0.65
     Niel
    -0.64
     Efe
    -0.63
    POSITIVE LOGITS
    Bead
    0.85
     Beads
    0.82
     Bead
    0.81
     beads
    0.78
     Antoni
    0.76
     Coaster
    0.75
     bead
    0.73
     OY
    0.71
     Pearce
    0.71
     Lumin
    0.70
    Activations Density 1.721%

    No Known Activations