© 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. 42386
    Prev
    Next
    INDEX
    Explanations

    rid

    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
    oa̍t
    -0.82
    ErrorListener
    -0.77
    expandindo
    -0.74
    GEBURTSDATUM
    -0.73
     TestBed
    -0.70
    
    -0.69
    LookAnd
    -0.68
    BASEPATH
    -0.67
    ьаж
    -0.66
     strings
    -0.64
    POSITIVE LOGITS
     of
    1.00
    теризу
    0.50
    culously
    0.50
     dessus
    0.48
    tidaknya
    0.47
     mayoría
    0.46
     fortemente
    0.45
     disposent
    0.45
     completamente
    0.45
     épaules
    0.45
    Activations Density 0.050%

    No Known Activations