© 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. 20-CLT-HP
    7. 74858
    Prev
    Next
    INDEX
    Explanations

    code generation

    np_max-act-logits · 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
    học
    -0.57
    AutoField
    -0.54
    tibles
    -0.54
    yi
    -0.53
     uska
    -0.50
    FDRE
    -0.48
     LUMP
    -0.47
    ISODE
    -0.46
    ereur
    -0.46
     SYLLABLE
    -0.45
    POSITIVE LOGITS
    AndEndTag
    0.66
    UnusedPrivate
    0.65
    LookAnd
    0.60
     estekak
    0.59
     فريبيس
    0.59
    ForRow
    0.58
    Tembelea
    0.57
    AccessorTable
    0.57
     referenties
    0.56
    ########.
    0.55
    Activations Density 0.014%

    No Known Activations