© 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. 97317
    Prev
    Next
    INDEX
    Explanations

    mall stadium

    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
     arena
    -0.72
     mall
    -0.69
     stadium
    -0.69
     venue
    -0.65
    ien
    -0.64
    venue
    -0.64
     Venue
    -0.63
    //*[@
    -0.62
    Venue
    -0.62
    ized
    -0.61
    POSITIVE LOGITS
     Abbé
    0.59
     crystall
    0.54
     integrable
    0.53
     Shakspeare
    0.52
     Jesuits
    0.52
     Algarve
    0.51
    <bos>
    0.51
    enumi
    0.51
     alpina
    0.50
     landings
    0.50
    Activations Density 0.202%

    No Known Activations