© 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. 10504
    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
    brio
    -0.54
    larna
    -0.52
     Listening
    -0.49
    MigrationBuilder
    -0.48
    Listening
    -0.48
    richTextPanel
    -0.48
     Lennon
    -0.47
     nyel
    -0.47
     musicales
    -0.47
     aveug
    -0.47
    POSITIVE LOGITS
    cshtml
    0.62
    -------
    0.58
    IonicModule
    0.56
     ProtoMessage
    0.55
     dán
    0.54
    }$​
    0.54
    Билгалдахарш
    0.54
    ]")]
    0.52
    instancetype
    0.52
     EnglishChoose
    0.52
    Activations Density 0.049%

    No Known Activations