© 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. 75061
    Prev
    Next
    INDEX
    Explanations

    eye

    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
     createState
    -0.57
     لينك
    -0.52
    .*")]
    -0.50
    ριο
    -0.49
    nya
    -0.49
     дописавши
    -0.48
    ness
    -0.47
     parlant
    -0.47
    ship
    -0.46
     đảo
    -0.46
    POSITIVE LOGITS
     ArrayAdapter
    0.58
     LoggerFactory
    0.58
    EnableWeb
    0.53
    Enllaços
    0.49
    सन्दर्भ
    0.48
     strain
    0.48
     Вікі
    0.47
    gms
    0.47
     brows
    0.46
     masks
    0.46
    Activations Density 0.005%

    No Known Activations