© 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. 1-CLT-HP
    7. 13541
    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
     O
    -0.41
    ագրություններ
    -0.40
    middleware
    -0.38
    itec
    -0.37
    Store
    -0.37
     cer
    -0.37
    यर
    -0.36
    FontOfSize
    -0.36
     createStore
    -0.36
    \(
    -0.35
    POSITIVE LOGITS
     Majefty
    0.76
     Houſe
    0.74
     ModelRenderer
    0.72
     quæ
    0.71
     Anſ
    0.70
     mergeFrom
    0.70
    клопе
    0.69
     chóng
    0.68
     purpoſe
    0.68
    ENDIX
    0.67
    Activations Density 0.054%

    No Known Activations