© 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. 2361
    Prev
    Next
    INDEX
    Explanations

    the word "were" or "was"

    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
     they
    -0.73
    他们是
    -0.71
     their
    -0.67
    s
    -0.64
    AreEqual
    -0.62
     THEY
    -0.61
    they
    -0.58
    にいる
    -0.57
    yorlar
    -0.57
    THEY
    -0.57
    POSITIVE LOGITS
    PerformLayout
    0.81
    $_['
    0.65
    ächs
    0.64
    SuspendLayout
    0.63
     Dieter
    0.63
    ymce
    0.63
    AddTagHelper
    0.61
     INTERESAR
    0.61
    oen
    0.61
    rasında
    0.60
    Activations Density 0.254%

    No Known Activations