© 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. 958
    Prev
    Next
    INDEX
    Explanations

    blocks of number-like sequences that represent dates, times, or versions

    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
    Tazama
    -0.56
     conclusão
    -0.56
     fournisseurs
    -0.50
    Odkazy
    -0.47
     épaules
    -0.47
     fallecido
    -0.46
    المراجع
    -0.46
     huiles
    -0.46
     oreilles
    -0.45
     möjlighet
    -0.45
    POSITIVE LOGITS
    帖最后由
    0.86
     ***!
    0.81
    StoryboardSegue
    0.71
    ScopeManager
    0.67
    ValueStyle
    0.67
    posedge
    0.66
     estekak
    0.65
    Diweddarwch
    0.65
     viewType
    0.65
    سطس
    0.64
    Activations Density 0.173%

    No Known Activations