© 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. 5-CLT-HP
    4. 393
    Prev
    Next
    INDEX
    Explanations

    examining

    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
    tvguidetime
    -0.62
    OfBirth
    -0.51
    Kjelder
    -0.48
    getSystemService
    -0.48
    ThroughAttribute
    -0.48
    Lähteet
    -0.47
     EconPapers
    -0.47
    씩
    -0.47
    zei
    -0.47
     Plus
    -0.43
    POSITIVE LOGITS
    %)$
    0.65
    OrNil
    0.61
    rawDesc
    0.59
     становника
    0.57
    Хьажоргаш
    0.57
     propOrder
    0.57
     apnea
    0.54
    reon
    0.54
     **/
    
    0.53
     >=",
    0.52
    Activations Density 0.005%

    No Known Activations