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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93799
    Prev
    Next
    INDEX
    Explanations

    come

    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
     your
    -0.74
    MemoryWarning
    -0.72
    IntoConstraints
    -0.62
    HtmlAttribute
    -0.59
     DriverManager
    -0.57
    principalTable
    -0.55
    your
    -0.55
    ComponentModel
    -0.55
    calls
    -0.54
    دانشنامهٔ
    -0.53
    POSITIVE LOGITS
    Chham
    0.63
     face
    0.62
    extAlignment
    0.56
    Скачать
    0.56
    期刊论文
    0.53
    ఔ
    0.51
     Protobuf
    0.50
     sit
    0.50
    ิ้ง
    0.49
     home
    0.49
    Activations Density 0.004%

    No Known Activations