© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14241
    Prev
    Next
    INDEX
    Explanations

    Music or Ballet

    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
     Orchestra
    -0.75
     choir
    -0.68
     Choir
    -0.65
    WireFormatLite
    -0.65
    XmlAccessType
    -0.61
     orchestra
    -0.59
    AndEndTag
    -0.59
    цездатний
    -0.57
     Chor
    -0.56
     choirs
    -0.55
    POSITIVE LOGITS
    rrggbb
    0.62
    ГЛА
    0.60
    sanitize
    0.59
     Sweep
    0.56
    peutic
    0.56
    glie
    0.55
    oba
    0.54
    TAWA
    0.54
    SurfaceView
    0.51
     netto
    0.51
    Activations Density 0.029%

    No Known Activations