© 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. 2111
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to rules, models, and expressing opinions

    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
     itſelf
    -0.90
     myſelf
    -0.80
     moschino
    -0.79
    ſelf
    -0.76
     ་་
    -0.75
     مرئيه
    -0.74
     Shakspeare
    -0.68
    ſelves
    -0.68
     iſt
    -0.68
     كومونز
    -0.68
    POSITIVE LOGITS
     Bro
    0.65
    ing
    0.58
     L
    0.58
    ற்ப
    0.56
     ur
    0.56
     Fra
    0.55
    bolite
    0.54
     C
    0.53
    曖昧さ回避
    0.53
     ویکی‌پدیا
    0.53
    Activations Density 1.428%

    No Known Activations