© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-RES-MATRYOSHKA-DC
    7. 1218
    Prev
    Next
    INDEX
    Explanations

    references to the defining attributes or features of a measurable entity or process

    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
     property
    -0.72
     Property
    -0.63
    Property
    -0.63
     الاطلاع
    -0.59
    IBOutlet
    -0.57
    property
    -0.57
     للمعارف
    -0.57
     Վերցված
    -0.56
     violences
    -0.56
    법
    -0.54
    POSITIVE LOGITS
     characteristic
    3.19
     Characteristic
    2.92
     characteristics
    2.72
    characteristic
    2.70
     Characteristics
    2.69
    Characteristic
    2.55
    characteristics
    2.50
    Characteristics
    2.47
     caractéristique
    2.31
     CHARACTERISTICS
    2.25
    Activations Density 0.405%

    No Known Activations