© 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. 1537
    Prev
    Next
    INDEX
    Explanations

    Mixed languages and code

    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
    anthe
    -2.11
    anthem
    -0.60
     ansatte
    -0.51
     täv
    -0.51
    GetAxis
    -0.50
    AutoSize
    -0.45
    cinhas
    -0.45
     därför
    -0.44
     tør
    -0.44
     eneste
    -0.43
    POSITIVE LOGITS
    awaiter
    0.73
     وتسجيلات
    0.64
    MediaStore
    0.62
     محفوظة
    0.61
    AutoresizingMask
    0.56
    PMailer
    0.56
    ScopeManager
    0.56
    原始内容存档于
    0.56
    Jereo
    0.56
     NSCoder
    0.56
    Activations Density 0.243%

    No Known Activations