© 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. 0-CLT-HP
    7. 42328
    Prev
    Next
    INDEX
    Explanations

    trapping or genera

    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
     trap
    -2.00
     traps
    -1.77
     trapping
    -1.72
     Trap
    -1.63
    trap
    -1.57
     Traps
    -1.49
     trapped
    -1.45
    Trap
    -1.38
     TRAP
    -1.23
    TRAP
    -1.03
    POSITIVE LOGITS
     fato
    0.54
    pa
    0.53
    call
    0.51
    set
    0.50
    spec
    0.49
     internes
    0.49
     sesuai
    0.49
     Waray
    0.48
    Gr
    0.47
    see
    0.47
    Activations Density 0.030%

    No Known Activations