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. 9-RES-MATRYOSHKA-DC
    4. 16513
    Prev
    Next
    INDEX
    Explanations

    the word "study" preceded by a comma

    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
    sizeCache
    -0.82
    principalTable
    -0.72
    MeasureSpec
    -0.65
     TextAlign
    -0.63
    PreferredItem
    -0.61
    eleste
    -0.61
    bitField
    -0.60
    onViewCreated
    -0.59
    发表于
    -0.58
    mazoo
    -0.57
    POSITIVE LOGITS
     }}$}
    0.66
     Alam
    0.65
    ]";
    0.62
    })$}
    0.59
    EME
    0.58
     désolés
    0.58
    enzio
    0.58
    celia
    0.58
     Albright
    0.57
    Initi
    0.57
    Activations Density 0.028%

    No Known Activations