© 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. 94459
    Prev
    Next
    INDEX
    Explanations

    code

    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
    :✨
    -0.51
     aandacht
    -0.47
    ",$
    -0.45
     Infórmanos
    -0.45
    써
    -0.42
     AssemblyTitle
    -0.42
    expandindo
    -0.41
     barriga
    -0.41
    География
    -0.40
    untitled
    -0.40
    POSITIVE LOGITS
    twimg
    0.64
    opic
    0.54
    rogens
    0.52
    ovec
    0.52
    iibo
    0.52
    unhofer
    0.51
     Fingerprint
    0.51
     Theſe
    0.51
    vacy
    0.51
    bilt
    0.51
    Activations Density 0.008%

    No Known Activations