© 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. 0-CLT-HP
    7. 1926
    Prev
    Next
    INDEX
    Explanations

    sett

    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
     TextAppearance
    -0.75
     religieuses
    -0.75
     aplican
    -0.70
     sauvages
    -0.70
     pinulongan
    -0.69
    __*/
    -0.67
    IntoConstraints
    -0.67
     colorés
    -0.67
     blessés
    -0.66
     salvajes
    -0.66
    POSITIVE LOGITS
    ism
    0.63
    zon
    0.52
     zon
    0.51
    ery
    0.47
     boundaries
    0.47
     Pad
    0.47
    ries
    0.46
    ison
    0.45
     Zir
    0.45
    roek
    0.45
    Activations Density 0.036%

    No Known Activations