© 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. 0-CLT-HP
    7. 43543
    Prev
    Next
    INDEX
    Explanations

    (

    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
     kok
    -0.52
    '
    -0.52
     الحره
    -0.51
    ,
    -0.51
    ier
    -0.48
     men
    -0.45
     sco
    -0.45
    ';
    -0.45
     tri
    -0.44
    ler
    -0.44
    POSITIVE LOGITS
     feroit
    0.96
    ↵
    0.92
     étoient
    0.90
     auroit
    0.87
     avoient
    0.84
     pouvoit
    0.84
     étoit
    0.81
     définiti
    0.80
     enfans
    0.78
     ainfi
    0.77
    Activations Density 1.386%

    No Known Activations