© 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. 4514
    Prev
    Next
    INDEX
    Explanations

    convention

    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
    caccio
    -0.80
    ніципалі
    -0.71
    EndGlobalSection
    -0.60
    ///</
    -0.52
    gameserver
    -0.48
     geslacht
    -0.47
    DockStyle
    -0.46
    ath
    -0.45
    AndroidJUnit
    -0.45
    aths
    -0.44
    POSITIVE LOGITS
     Efq
    0.69
     whoſe
    0.62
     myſelf
    0.60
     DBNull
    0.59
     Noch
    0.57
     Monfieur
    0.57
    Intial
    0.56
     Arian
    0.56
    WebVitals
    0.55
     becauſe
    0.54
    Activations Density 0.001%

    No Known Activations