© 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. 2057
    Prev
    Next
    INDEX
    Explanations

    blue

    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
     ancient
    -0.79
     subject
    -0.78
     chosen
    -0.71
     Grecs
    -0.69
    ancient
    -0.65
    chosen
    -0.64
     brancas
    -0.63
     emplois
    -0.59
     étrangères
    -0.59
     vermelhas
    -0.59
    POSITIVE LOGITS
    <bos>
    0.79
    Autoritní
    0.73
    StoryboardSegue
    0.68
    protoimpl
    0.67
     <=",
    0.66
    ніципа
    0.65
    PerformLayout
    0.60
     мәкал
    0.58
    ized
    0.57
     kaynağından
    0.57
    Activations Density 0.106%

    No Known Activations