© 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. 0-RES-MATRYOSHKA-DC
    7. 12006
    Prev
    Next
    INDEX
    Explanations

    code snippets related to moving or relocating objects

    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
    XmlAccessorType
    -0.63
     Вікі
    -0.61
     وتسجيلات
    -0.60
     متحده
    -0.58
     للمعارف
    -0.54
     lèvres
    -0.53
    createClass
    -0.51
    Externí
    -0.50
    ographia
    -0.50
     beur
    -0.50
    POSITIVE LOGITS
    mv
    0.85
     masculine
    0.84
     feminine
    0.75
    hemian
    0.73
     magnetism
    0.72
    stery
    0.72
     unknownFields
    0.71
    htdocs
    0.71
    serif
    0.69
    duc
    0.66
    Activations Density 0.034%

    No Known Activations