© 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. 43489
    Prev
    Next
    INDEX
    Explanations

    data/technical information

    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
    verwijspagina
    -0.69
    ij
    -0.68
    BeginContext
    -0.67
    i
    -0.64
     Jeff
    -0.62
    Jeff
    -0.61
    发表于
    -0.59
    httphttps
    -0.59
     المعيارى
    -0.58
    findpost
    -0.57
    POSITIVE LOGITS
     themſelves
    0.60
     myſelf
    0.59
     Majefty
    0.59
     Drapeau
    0.57
     Jefus
    0.57
     Theſe
    0.57
    tés
    0.53
    IntoConstraints
    0.52
     Tole
    0.51
    ల్ల
    0.50
    Activations Density 0.024%

    No Known Activations