© 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. 1108
    Prev
    Next
    INDEX
    Explanations

    mathematical terms, especially those involving symbols, algebra, and dimensionality

    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
     AssemblyCulture
    -0.65
    featureID
    -0.55
     JSTOR
    -0.50
    REVISION
    -0.50
    OGND
    -0.49
    InputBorder
    -0.48
    uasion
    -0.48
    ,**
    -0.48
    myname
    -0.48
     елның
    -0.47
    POSITIVE LOGITS
    $-
    1.13
    }$-
    0.82
    )$-
    0.76
    tonsoft
    0.62
    ianum
    0.61
    acterial
    0.58
    клопе
    0.56
    medriver
    0.55
    orological
    0.53
    chitz
    0.53
    Activations Density 0.239%

    No Known Activations