© 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. 4-CLT-HP
    7. 3025
    Prev
    Next
    INDEX
    Explanations

    about here

    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
     ब्रेकडाउन
    -0.75
    orianCalendar
    -0.68
    drinks
    -0.66
    verwijspagina
    -0.63
    ellees
    -0.62
    Parcelize
    -0.62
     blessé
    -0.62
    EndGlobalSection
    -0.61
     AssemblyTitle
    -0.60
     fallu
    -0.60
    POSITIVE LOGITS
     a
    0.51
     the
    0.50
    lossary
    0.45
    Werdegang
    0.44
     quadri
    0.44
    QMetaType
    0.41
    sendStatus
    0.41
     settling
    0.40
     settlement
    0.40
     that
    0.40
    Activations Density 0.004%

    No Known Activations