© 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. 9550
    Prev
    Next
    INDEX
    Explanations

    music and singing

    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
    RetentionPolicy
    -0.65
     étend
    -0.60
     commercio
    -0.56
     coucher
    -0.55
     conseguenza
    -0.55
    YJ
    -0.54
    XMLSchema
    -0.54
    KURZBESCHREIBUNG
    -0.52
     campamento
    -0.52
    chapper
    -0.52
    POSITIVE LOGITS
     vnd
    0.56
    Geplaatst
    0.53
     Italijani
    0.51
    oneph
    0.51
    line
    0.50
     monoch
    0.50
     Walkover
    0.48
    alige
    0.48
     Min
    0.48
    Min
    0.47
    Activations Density 0.014%

    No Known Activations