© 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
    2. Gemma-2-2B
    3. 2-RES-MATRYOSHKA-DC
    4. 4166
    Prev
    Next
    INDEX
    Explanations

    references to mechanical components involved in coupling and support structures

    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
     quæ
    -0.83
     étoit
    -0.78
     pouvoit
    -0.73
     avoient
    -0.72
     militaires
    -0.71
     démocr
    -0.69
     médicaux
    -0.68
     définiti
    -0.68
     figliu
    -0.68
     Grecs
    -0.68
    POSITIVE LOGITS
    }")]
    0.82
    BeginContext
    0.77
    cjach
    0.71
    %");
    0.71
     IBOutlet
    0.69
    }`}>
    0.69
    ."));
    0.67
     GenerationType
    0.66
    }">
    0.66
     برانيه
    0.66
    Activations Density 2.549%

    No Known Activations