© 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. 1926
    Prev
    Next
    INDEX
    Explanations

    terms related to properties or qualities of something, often with suffixes like "-ness", "-ity", or indicating security or order

    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
     Mather
    -0.61
     reaſon
    -0.61
     endregion
    -0.61
    ്ട
    -0.60
     Survey
    -0.59
     dõi
    -0.58
     dụ
    -0.57
     piacevole
    -0.57
     SURVEY
    -0.57
    oform
    -0.56
    POSITIVE LOGITS
    ness
    1.21
    iteness
    1.16
     robustness
    1.13
    teness
    1.12
    tability
    1.11
    iness
    1.10
     stability
    1.09
     completeness
    1.09
     sterility
    1.09
     linearity
    1.08
    Activations Density 1.100%

    No Known Activations