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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-RES-MATRYOSHKA-DC
    4. 31134
    Prev
    Next
    INDEX
    Explanations

    technical descriptions of modifying physical objects

    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
    MLLoader
    -0.71
    DockStyle
    -0.56
     समीक्षक
    -0.54
     Mancha
    -0.54
     tủ
    -0.53
    Vaata
    -0.51
    cheinend
    -0.51
    arkt
    -0.50
     фак
    -0.49
    enterOuterAlt
    -0.49
    POSITIVE LOGITS
    expandindo
    0.74
     שוליים
    0.68
     ControllerBase
    0.59
     convertView
    0.55
     onResponse
    0.55
     <=",
    0.55
    المكان
    0.54
     createState
    0.53
     adapters
    0.53
     unknownFields
    0.52
    Activations Density 0.076%

    No Known Activations