© 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. 0-RES-MATRYOSHKA-DC
    7. 12343
    Prev
    Next
    INDEX
    Explanations

    patterns related to multiplicities or counts within data

    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
     nakalista
    -0.69
     surla
    -0.68
     initComponents
    -0.66
    ыгана
    -0.62
    دانشنامهٔ
    -0.61
    icated
    -0.60
     resourceCulture
    -0.60
    AddTagHelper
    -0.60
    readFileSync
    -0.59
     ThemeData
    -0.58
    POSITIVE LOGITS
     multiplicity
    2.03
    multip
    1.31
     multip
    1.29
    Multip
    1.16
     Multip
    1.11
     multiplic
    0.63
     AspNetCore
    0.57
     bronchial
    0.56
    ratt
    0.55
    zzi
    0.52
    Activations Density 0.006%

    No Known Activations