© 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. 12165
    Prev
    Next
    INDEX
    Explanations

    words related to specific lexical features or linguistic attributes

    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
    TagMode
    -0.67
     незавершена
    -0.65
    AndroidJUnit
    -0.64
    urb
    -0.63
    SourceChecksum
    -0.60
    adaptiveStyles
    -0.59
    iecie
    -0.59
    webElementXpaths
    -0.58
    PyExc
    -0.57
    fjspx
    -0.57
    POSITIVE LOGITS
    性
    3.48
    性的
    2.61
    性の
    2.23
     性
    2.22
    性和
    2.20
    性を
    2.03
    性は
    1.95
    性に
    1.85
    性が
    1.81
    성
    1.73
    Activations Density 0.000%

    No Known Activations