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. 16676
    Prev
    Next
    INDEX
    Explanations

    language related to health and well-being including greetings with the word "how" in them

    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
    ste
    -0.54
     design
    -0.52
    Exceeded
    -0.51
     n
    -0.51
     big
    -0.50
     Bài
    -0.49
     implement
    -0.48
    外部リンク
    -0.48
    Schon
    -0.48
     Per
    -0.47
    POSITIVE LOGITS
    IntoConstraints
    1.07
     ſtate
    0.94
     ftate
    0.85
     상태
    0.85
     condizioni
    0.82
     itſelf
    0.82
     statuses
    0.80
     état
    0.79
     createState
    0.79
     myſelf
    0.79
    Activations Density 0.141%

    No Known Activations