© 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. 9535
    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
     pinulongan
    -1.05
    SharedDtor
    -0.84
    EndContext
    -0.83
     poffible
    -0.81
    seamnă
    -0.81
    awaiter
    -0.79
    OrBuilder
    -0.77
    WireFormatLite
    -0.77
    berdayakan
    -0.76
     engraçadas
    -0.75
    POSITIVE LOGITS
     son
    0.45
    putan
    0.43
    Subview
    0.41
     col
    0.39
     no
    0.38
    ante
    0.38
     Sis
    0.38
     Gris
    0.38
    Ante
    0.38
    ion
    0.38
    Activations Density 0.088%

    No Known Activations