© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1081
    Prev
    Next
    INDEX
    Explanations

    been

    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
    NameInMap
    -0.73
    ModelAdmin
    -0.66
     OFDb
    -0.65
    StoryboardSegue
    -0.62
    twimg
    -0.60
     Dox
    -0.60
     Pyle
    -0.59
    homonymie
    -0.57
    Personensuche
    -0.57
     चीज़ों
    -0.57
    POSITIVE LOGITS
     quello
    0.57
     rêves
    0.54
    الحياه
    0.50
     concernés
    0.48
     normales
    0.47
    intellij
    0.47
     mijne
    0.47
     individuales
    0.47
     atunci
    0.46
     henkil
    0.46
    Activations Density 0.005%

    No Known Activations