© 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. 1-RES-MATRYOSHKA-DC
    7. 15
    Prev
    Next
    INDEX
    Explanations

    patterns related to numerical or coded identifiers, such as version numbers or configuration codes

    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
     disambiguazione
    -0.81
    2
    -0.72
    -0.68
    ingos
    -0.60
    ibatis
    -0.59
    icium
    -0.58
    ليه
    -0.57
    oplayer
    -0.57
    纸
    -0.56
     Lott
    -0.56
    POSITIVE LOGITS
    6
    2.16
     Six
    2.02
     SIX
    1.93
     six
    1.91
     Sixth
    1.90
     sixth
    1.85
    ⁶
    1.85
    Six
    1.75
    ６
    1.75
    SIX
    1.73
    Activations Density 5.096%

    No Known Activations