© 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. 20-CLT-HP
    7. 71933
    Prev
    Next
    INDEX
    Explanations

    programming/technical contexts

    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
     newBuilder
    -0.63
     صوتيه
    -0.60
     ApiException
    -0.59
    Espa
    -0.54
     Kohl
    -0.52
    Зноскі
    -0.50
     Kush
    -0.50
    Manbalar
    -0.49
    Искәрмәләр
    -0.48
     ProtoMessage
    -0.48
    POSITIVE LOGITS
    BarStyle
    0.50
     bedo
    0.50
    Affirmed
    0.50
    TextWatcher
    0.48
    Ingrédients
    0.48
     Fiche
    0.48
    LookAnd
    0.47
    doctype
    0.46
    Zutaten
    0.46
     nekem
    0.46
    Activations Density 0.000%

    No Known Activations