© 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. 4-CLT-HP
    7. 2176
    Prev
    Next
    INDEX
    Explanations

    Medical tests and elements

    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
     Hart
    -0.56
    recta
    -0.52
     motor
    -0.52
     Lin
    -0.51
     Put
    -0.50
    Linea
    -0.50
     engine
    -0.49
     Engine
    -0.49
    ints
    -0.48
    auto
    -0.48
    POSITIVE LOGITS
    WireFormatLite
    0.82
    OGND
    0.79
     ProtoMessage
    0.79
    Personendaten
    0.73
    SequentialGroup
    0.71
    Personensuche
    0.70
    +:+
    0.67
    IntoConstraints
    0.65
    VIAF
    0.64
     تضيفلها
    0.63
    Activations Density 0.005%

    No Known Activations