© 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. 38315
    Prev
    Next
    INDEX
    Explanations

    programming/coding

    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
    ंदीखरीदारी
    -0.86
    Демографія
    -0.84
    FieldBuilder
    -0.71
     الحره
    -0.70
    adaptiveStyles
    -0.69
     estekak
    -0.67
    Diweddarwch
    -0.67
    buttonShape
    -0.65
    "):
    -0.64
    UnknownFields
    -0.63
    POSITIVE LOGITS
    paddingVertical
    0.65
    BeginContext
    0.51
    هی
    0.51
     Rip
    0.49
     kalan
    0.46
     Biophys
    0.46
    sique
    0.45
    pannt
    0.45
     Section
    0.45
     curse
    0.44
    Activations Density 0.075%

    No Known Activations