© 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. 0-CLT-HP
    7. 38377
    Prev
    Next
    INDEX
    Explanations

    Music albums/records

    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
     Records
    -0.62
    AxisAlignment
    -0.55
    RenderAtEndOf
    -0.49
    ec
    -0.48
    lot
    -0.48
    +:+
    -0.48
    QA
    -0.47
     للاسماء
    -0.47
    ant
    -0.47
     soát
    -0.47
    POSITIVE LOGITS
    rxjs
    0.64
     gericht
    0.60
     Complexes
    0.59
     NgModule
    0.57
     صوتيه
    0.56
     purpoſe
    0.54
     Platforms
    0.54
     CommonModule
    0.53
     Maury
    0.53
    truc
    0.52
    Activations Density 0.282%

    No Known Activations