© 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. 2-RES-MATRYOSHKA-DC
    7. 2829
    Prev
    Next
    INDEX
    Explanations

    segments of repetitive or identical placeholder text

    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
    RefNanny
    -0.79
     محفوظة
    -0.73
     SHR
    -0.73
     resourceCulture
    -0.71
    setVerticalGroup
    -0.71
    ISupport
    -0.70
    XtraReports
    -0.70
    endphp
    -0.68
     propOrder
    -0.68
     Offisielt
    -0.67
    POSITIVE LOGITS
    blaze
    3.03
    bla
    2.81
    Bla
    2.73
     bla
    2.70
     Bla
    2.70
    Blaze
    2.13
    BLA
    2.11
     BLA
    2.05
     Blaze
    1.84
     blaze
    1.71
    Activations Density 0.045%

    No Known Activations