© 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. 6-RES-MATRYOSHKA-DC
    7. 44
    Prev
    Next
    INDEX
    Explanations

    years represented as four-digit numbers, often with additional formatting such as commas

    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
    vstack
    -0.58
    diğ
    -0.56
    vč
    -0.56
     équilibre
    -0.56
    pable
    -0.55
     altrett
    -0.55
    stück
    -0.53
     intelig
    -0.53
    assertRaises
    -0.52
    ctile
    -0.52
    POSITIVE LOGITS
     year
    1.04
    year
    0.95
     years
    0.93
    년
    0.91
     OFDb
    0.90
    years
    0.90
     decade
    0.89
    年
    0.81
    ⓧ
    0.81
     ExecuteAsync
    0.80
    Activations Density 1.717%

    No Known Activations