© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91424
    Prev
    Next
    INDEX
    Explanations

    international

    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
     propOrder
    -0.75
    awtextra
    -0.69
    VersionUID
    -0.63
    ftagPool
    -0.62
    Décès
    -0.61
    PDOException
    -0.59
    Бахар
    -0.57
     Bracken
    -0.57
    DebuggerStep
    -0.56
    __((
    -0.56
    POSITIVE LOGITS
    GEBURTSDATUM
    0.50
     AssemblyCulture
    0.45
     nocturne
    0.42
     ambientale
    0.42
    Flickr
    0.42
    E
    0.42
     givet
    0.42
     Ai
    0.42
     vastaan
    0.41
    AW
    0.40
    Activations Density 0.002%

    No Known Activations