© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 92430
    Prev
    Next
    INDEX
    Explanations

    "fordshire"

    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
    fordshire
    -0.91
     Niz
    -0.79
     whereof
    -0.78
    StoryboardSegue
    -0.64
     Swat
    -0.62
     LPC
    -0.60
     nahilalakip
    -0.60
     Référence
    -0.58
    textTheme
    -0.56
    +:+
    -0.56
    POSITIVE LOGITS
    PageModule
    0.53
    PerformLayout
    0.49
    RepeatedField
    0.48
    NewUrlParser
    0.46
    schul
    0.45
    bootstrapcdn
    0.45
    ocarditis
    0.44
    brar
    0.44
     automaticamente
    0.43
    Ữ
    0.43
    Activations Density 1.670%

    No Known Activations