© 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. 3392
    Prev
    Next
    INDEX
    Explanations

    references to specific key personnel or identifiers

    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
    k
    -1.45
     k
    -1.01
    K
    -0.80
    к
    -0.70
     K
    -0.62
    ik
    -0.62
    𝑘
    -0.60
    𝐤
    -0.57
     Chak
    -0.57
    𝙠
    -0.56
    POSITIVE LOGITS
     KP
    1.10
     KC
    1.02
     Kenner
    1.00
     Kanz
    0.99
     KR
    0.96
     KOR
    0.95
     KDE
    0.94
     KJ
    0.94
    fjspx
    0.94
     Kare
    0.93
    Activations Density 0.212%

    No Known Activations