© 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. 0-CLT-HP
    7. 40503
    Prev
    Next
    INDEX
    Explanations

    music

    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
     ring
    -0.67
     Good
    -0.50
     Hill
    -0.47
     Mal
    -0.44
     AM
    -0.38
     Morning
    -0.38
    Zm
    -0.37
    AOC
    -0.37
    ตะ
    -0.36
    Hill
    -0.35
    POSITIVE LOGITS
    ian
    0.91
     AssemblyTitle
    0.90
    ніципалі
    0.87
    bootstrapcdn
    0.87
    LEncoder
    0.86
    insee
    0.83
     pinulongan
    0.82
    ioutil
    0.82
    QMetaType
    0.79
    Geplaatst
    0.77
    Activations Density 0.077%

    No Known Activations