© 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. 2000
    Prev
    Next
    INDEX
    Explanations

    the prefix "un" denoting negation or lack of something.

    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
    )))));
    -0.84
    IBOutlet
    -0.79
    SpringBootTest
    -0.74
    httphttps
    -0.73
     ExecuteAsync
    -0.70
     Darryl
    -0.69
     RVA
    -0.68
     Référence
    -0.67
     وتسجيلات
    -0.67
    zości
    -0.65
    POSITIVE LOGITS
     Un
    1.94
     un
    1.90
    Un
    1.76
     UN
    1.54
     unt
    1.48
     Uns
    1.45
    un
    1.43
     Unt
    1.37
     unre
    1.36
     unw
    1.35
    Activations Density 0.576%

    No Known Activations