© 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. 4-CLT-HP
    7. 464
    Prev
    Next
    INDEX
    Explanations

    technical/programming text

    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
     TextInputType
    -0.61
    MigrationBuilder
    -0.59
     <=",
    -0.57
    KURZBESCHREIBUNG
    -0.56
     pressing
    -0.55
     Sélectionnez
    -0.54
    ABUL
    -0.54
     оригіналу
    -0.54
    uvres
    -0.54
     Sumatra
    -0.54
    POSITIVE LOGITS
     înce
    0.48
    En
    0.46
     oscu
    0.42
    Dug
    0.42
    yó
    0.42
    Row
    0.42
    SequentialGroup
    0.41
    RegressionTest
    0.41
    󠁴
    0.40
     intptr
    0.40
    Activations Density 0.003%

    No Known Activations