© 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. 3-RES-MATRYOSHKA-DC
    7. 2245
    Prev
    Next
    INDEX
    Explanations

    the word "point" and words associated to it in math papers

    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
     setuptools
    -0.62
     Савезне
    -0.60
    ]]]
    -0.57
    @[+][
    -0.57
     transfieras
    -0.57
    rawDesc
    -0.56
    __.__
    -0.55
    ysacchar
    -0.53
    StoreMessageInfo
    -0.52
    :][
    -0.50
    POSITIVE LOGITS
     سكانية
    0.60
    tvguidetime
    0.59
     solitude
    0.56
    atella
    0.55
    ripe
    0.54
     Schuster
    0.52
    Lưu
    0.52
     lonely
    0.52
     wards
    0.52
     loneliness
    0.52
    Activations Density 0.029%

    No Known Activations