© 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. 92367
    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
    -1.41
     Model
    -1.17
    model
    -1.08
    Model
    -1.06
     MODEL
    -0.91
     modelo
    -0.88
     modèle
    -0.81
     모델
    -0.79
     Modell
    -0.79
    MODEL
    -0.77
    POSITIVE LOGITS
     Efq
    1.01
     يتيمه
    0.90
     Monfieur
    0.88
     consecration
    0.88
     ostavi
    0.84
     myſelf
    0.84
     Anſ
    0.84
     Cæsar
    0.82
     pleaſure
    0.82
     becauſe
    0.82
    Activations Density 0.574%

    No Known Activations