© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 45379
    Prev
    Next
    INDEX
    Explanations

    class

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.98
    دانشنامهٔ
    -0.81
    TypedDataSet
    -0.79
     оригіналу
    -0.78
     []:
    -0.71
    WebServlet
    -0.71
     himo
    -0.71
    expandindo
    -0.70
    ThroughAttribute
    -0.69
    下载附件
    -0.66
    POSITIVE LOGITS
    <bos>
    0.55
    eful
    0.49
    XDECREF
    0.45
    harapkan
    0.43
     full
    0.42
     păr
    0.40
     penuh
    0.40
    umumkan
    0.40
     труда
    0.40
    istique
    0.39
    Activations Density 0.090%

    No Known Activations