© 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. 72055
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     nahilalakip
    -1.19
     للمعارف
    -0.82
    oredCriteria
    -0.81
    enumii
    -0.77
    //
    -0.72
    protoimpl
    -0.72
     EconPapers
    -0.69
     שוליים
    -0.68
    GraphicsUnit
    -0.68
    LabelTagHelper
    -0.67
    POSITIVE LOGITS
     M
    0.56
     be
    0.52
     BE
    0.50
    M
    0.45
     bev
    0.44
    NotBe
    0.44
     Be
    0.42
     MY
    0.42
    be
    0.41
     М
    0.39
    Activations Density 0.000%

    No Known Activations