© 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. 90468
    Prev
    Next
    INDEX
    Explanations

    model

    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
     model
    -1.42
    model
    -1.12
     Model
    -0.78
     модель
    -0.78
     modelo
    -0.77
    Model
    -0.76
     MODEL
    -0.72
     modèle
    -0.69
    modell
    -0.69
     محفوظة
    -0.63
    POSITIVE LOGITS
     itſelf
    1.09
     Efq
    0.90
     Houſe
    0.90
     myſelf
    0.79
     Cæsar
    0.78
     Majefty
    0.78
     Diſ
    0.77
     themſelves
    0.77
     himſelf
    0.76
     raiſ
    0.76
    Activations Density 0.121%

    No Known Activations