Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-RES-MATRYOSHKA-DC
    4. 31364
    Prev
    Next
    INDEX
    Explanations

    the word "Type" in code snippets

    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
    kespeare
    -0.75
    ductory
    -0.70
     Bader
    -0.69
    endphp
    -0.67
     chng
    -0.66
    tuig
    -0.65
    htë
    -0.65
    🗳
    -0.65
    ortic
    -0.64
    setNew
    -0.64
    POSITIVE LOGITS
     Woodruff
    0.88
     communautaire
    0.84
    GenerationType
    0.83
     Ziegler
    0.79
     Nani
    0.76
     nationaux
    0.75
     industriels
    0.75
     Donato
    0.75
     juges
    0.75
     Maat
    0.73
    Activations Density 0.011%

    No Known Activations