© 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. 1-CLT-HP
    7. 14753
    Prev
    Next
    INDEX
    Explanations

    question words

    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
     choose
    -0.49
     gekozen
    -0.48
     chose
    -0.47
    BeginContext
    -0.47
     choses
    -0.46
    j
    -0.46
     proposées
    -0.46
    Grace
    -0.46
    ikali
    -0.44
     EconPapers
    -0.44
    POSITIVE LOGITS
     AssemblyTitle
    0.78
    ]),
    0.76
    DoubleQuotes
    0.65
    WidgetItem
    0.64
    ModelSerializer
    0.63
    mergeFrom
    0.62
    forName
    0.62
    styleType
    0.61
     CallOverrides
    0.61
    LEncoder
    0.61
    Activations Density 0.015%

    No Known Activations