© 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. 3-RES-MATRYOSHKA-DC
    7. 1826
    Prev
    Next
    INDEX
    Explanations

    patent and application numbers

    oai_token-act-pair · gemini-2.0-flash
    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
     pleaſure
    -0.81
     ――――
    -0.77
     Theſe
    -0.75
    ſelf
    -0.74
    tslib
    -0.74
     gynhyrchwyd
    -0.74
     ―――――
    -0.73
    ſelves
    -0.72
     beſt
    -0.71
     ――――――――
    -0.71
    POSITIVE LOGITS
     Pat
    2.47
    Pat
    2.22
     pat
    2.03
    pat
    1.92
     PAT
    1.67
    PAT
    1.57
     Patent
    1.34
     PATENT
    1.27
    Patent
    1.20
     patent
    1.19
    Activations Density 0.224%

    No Known Activations