© 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. 1194
    Prev
    Next
    INDEX
    Explanations

    words starting with "un" and generally negative prefixes applied to words

    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
    httphttps
    -0.94
     BoxDecoration
    -0.84
     ***!
    -0.82
    )))));
    -0.79
    出版年
    -0.79
     RVA
    -0.77
    IBar
    -0.77
     وتسجيلات
    -0.77
    CardModule
    -0.75
    enumi
    -0.73
    POSITIVE LOGITS
     un
    1.61
     Un
    1.59
     UN
    1.34
    Un
    1.32
     unt
    1.19
     unre
    1.06
     unw
    1.02
     ung
    1.01
     Uns
    1.00
     UNS
    1.00
    Activations Density 0.638%

    No Known Activations