© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5180
    Prev
    Next
    INDEX
    Explanations

    instances of a specific symbolic or mathematical notation pattern involving superscripted exponents

    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
    }}_{\
    -0.82
    }}_{
    -0.81
    OGND
    -0.80
     Waterford
    -0.78
     Explora
    -0.77
     مواليد
    -0.75
     immobilier
    -0.72
    ^{
    -0.72
     Schuyler
    -0.71
     gången
    -0.71
    POSITIVE LOGITS
    }^
    2.05
    monix
    0.72
     estimés
    0.66
    djangoproject
    0.64
    TypedDataSet
    0.62
    mags
    0.57
    }^\
    0.57
     Mag
    0.57
    adget
    0.56
    )^
    0.56
    Activations Density 0.018%

    No Known Activations