© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 695
    Prev
    Next
    INDEX
    Explanations

    only

    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
    webElementXpaths
    -0.63
    InputBorder
    -0.58
    AndEndTag
    -0.57
    Scrolled
    -0.57
    unków
    -0.54
    setVerticalGroup
    -0.54
    SharedCtor
    -0.51
    jspx
    -0.51
    allclose
    -0.51
    styleable
    -0.49
    POSITIVE LOGITS
     steps
    0.62
    :\/\/
    0.59
    ]--;
    0.58
    ChildScrollView
    0.54
     AssemblyTitle
    0.54
     }}"></
    0.54
     stairs
    0.51
    steps
    0.49
     rocks
    0.49
    Steps
    0.48
    Activations Density 0.002%

    No Known Activations