© 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. 307
    Prev
    Next
    INDEX
    Explanations

    words related to math and science 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
    norsk
    -0.76
    <bos>
    -0.74
    はじめに
    -0.71
    ✨:
    -0.69
     Sawyer
    -0.68
    Демографія
    -0.68
    rsiniz
    -0.68
    DoubleQuotes
    -0.68
    rungsseite
    -0.67
    MMdd
    -0.66
    POSITIVE LOGITS
    ledem
    0.81
    </caption>
    0.79
    ApiModelProperty
    0.79
     pursuant
    0.74
     debido
    0.73
     tungkol
    0.73
    Ссылка
    0.72
     Grâce
    0.71
     الرغم
    0.71
     Acerca
    0.70
    Activations Density 3.644%

    No Known Activations