© 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. 5-CLT-HP
    7. 94748
    Prev
    Next
    INDEX
    Explanations

    bucket

    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
     qualités
    -0.58
    itschrift
    -0.53
     bâtiments
    -0.52
     lèvres
    -0.52
    AutoScale
    -0.51
     rispetto
    -0.51
    Rates
    -0.50
     épaules
    -0.50
     kuten
    -0.49
     suela
    -0.48
    POSITIVE LOGITS
     незавершена
    0.74
    WireFormatLite
    0.54
    audiovisuel
    0.52
    Hentet
    0.50
    փ
    0.50
    ThroughAttribute
    0.48
    SerializedSize
    0.48
    ctrica
    0.47
     محفوظة
    0.47
    ciatore
    0.47
    Activations Density 0.004%

    No Known Activations