© 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. 6860
    Prev
    Next
    INDEX
    Explanations

    expressions of mathematical bounds and inequalities

    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
     itſelf
    -0.72
     }}$}
    -0.66
     Shakspeare
    -0.63
    }();
    -0.61
     EconPapers
    -0.61
     rong
    -0.60
     мәкал
    -0.59
    !";
    -0.57
     })}
    -0.57
     anse
    -0.57
    POSITIVE LOGITS
    RegressionTest
    0.71
     Super
    0.55
     sanitarios
    0.52
    ztály
    0.52
    éri
    0.51
    oredCriteria
    0.51
    SuspendLayout
    0.50
    chauffer
    0.48
    autoconfigure
    0.47
     περι
    0.47
    Activations Density 0.362%

    No Known Activations