© 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. 76875
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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
    InitVars
    -0.53
    Bett
    -0.51
     Dars
    -0.51
     שוליים
    -0.50
    SourceChecksum
    -0.50
     cover
    -0.49
     Velo
    -0.49
     rospy
    -0.49
     cor
    -0.48
    Batis
    -0.47
    POSITIVE LOGITS
     contribué
    0.60
     refusé
    0.58
     enfans
    0.58
     voluto
    0.56
    LookAnd
    0.56
    ⓧ
    0.53
     المعيارى
    0.52
     changé
    0.52
     مؤرشف
    0.51
    djangoproject
    0.51
    Activations Density 0.000%

    No Known Activations