© 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. 92413
    Prev
    Next
    INDEX
    Explanations

    increased usage

    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
     adoption
    -0.93
    UserScript
    -0.86
    MemoryWarning
    -0.83
     Мексичка
    -0.82
    adoption
    -0.80
    berdayakan
    -0.79
     Planet
    -0.78
     Adoption
    -0.76
    Planet
    -0.75
    Portale
    -0.74
    POSITIVE LOGITS
     du
    0.60
    ally
    0.59
    es
    0.55
    ese
    0.49
    ный
    0.49
     den
    0.47
    al
    0.47
             
    0.46
     der
    0.46
    ного
    0.46
    Activations Density 0.057%

    No Known Activations