© 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. 77765
    Prev
    Next
    INDEX
    Explanations

    Weight and measurement

    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
     nakalista
    -0.48
     autorytatywna
    -0.47
    npmjs
    -0.43
    soort
    -0.40
    новниш
    -0.39
    ulan
    -0.38
     //$
    -0.38
     Goldsmith
    -0.38
     môi
    -0.38
     ?>>
    -0.38
    POSITIVE LOGITS
    
    0.74
     kN
    0.71
     ton
    0.69
     tons
    0.68
     tonnes
    0.66
     tonne
    0.66
    ruptedException
    0.65
    tonne
    0.64
    ton
    0.63
    sidemargin
    0.61
    Activations Density 0.000%

    No Known Activations