© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 71959
    Prev
    Next
    INDEX
    Explanations

    mixed language and code

    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
     Normdatei
    -0.47
     ekster
    -0.47
    تقاوى
    -0.47
     pieds
    -0.47
    UnsafeEnabled
    -0.46
     transfieras
    -0.40
    Jîn
    -0.39
    行
    -0.38
     suces
    -0.38
    áb
    -0.36
    POSITIVE LOGITS
     damp
    0.68
    IsPostBack
    0.65
     للمعارف
    0.64
    PerformLayout
    0.63
     safety
    0.63
     paddy
    0.63
     familiarity
    0.63
     concrete
    0.63
    sequelize
    0.62
    NUMX
    0.62
    Activations Density 0.000%

    No Known Activations