© 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. 302
    Prev
    Next
    INDEX
    Explanations

    source code and/or documents with very particular formatting and special characters

    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
     textStatus
    -0.65
     فريبيس
    -0.58
     adipis
    -0.57
    newArrayList
    -0.56
    hésite
    -0.55
     tắt
    -0.55
    ništ
    -0.52
    BagConstraints
    -0.52
    — 
    -0.52
    ยิ่ง
    -0.52
    POSITIVE LOGITS
    :✨
    0.80
    发表于
    0.79
     cherchés
    0.73
    Portail
    0.72
    tvguidetime
    0.70
     Upan
    0.69
    rungsseite
    0.68
     &___
    0.66
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.64
    ↵↵↵↵↵↵↵
    0.63
    Activations Density 6.615%

    No Known Activations