© 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. 20-CLT-HP
    4. 75201
    Prev
    Next
    INDEX
    Explanations

    math group theory

    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
     становника
    -0.62
    ➟
    -0.60
     createSlice
    -0.56
    
    -0.56
    andowski
    -0.55
     виправивши
    -0.55
    CreateModel
    -0.54
    erializer
    -0.53
    Rus
    -0.52
    örungen
    -0.52
    POSITIVE LOGITS
    EndTag
    0.53
    principalColumn
    0.48
     cucchiaio
    0.47
     normal
    0.47
    normal
    0.47
    TableHead
    0.46
    Normal
    0.45
     Normal
    0.44
     normaux
    0.43
     alimentaire
    0.42
    Activations Density 0.008%

    No Known Activations