© 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. 20-CLT-HP
    7. 75137
    Prev
    Next
    INDEX
    Explanations

    Technical abbreviations

    np_max-act-logits · 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
    Personendaten
    -0.55
    urium
    -0.50
     мәкалә
    -0.48
    ikou
    -0.48
     battery
    -0.48
     Quicks
    -0.47
     floor
    -0.47
    GPP
    -0.46
     reagents
    -0.46
     Kors
    -0.45
    POSITIVE LOGITS
    
    0.64
    DockStyle
    0.57
     surla
    0.56
     snippetHide
    0.55
    GraphicsUnit
    0.52
    StructEnd
    0.52
    Географи
    0.52
     Belgique
    0.51
    RegistryLite
    0.50
     insuffisamment
    0.49
    Activations Density 0.002%

    No Known Activations