© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1574
    Prev
    Next
    INDEX
    Explanations

    new opportunities

    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
     channels
    -0.68
     stations
    -0.67
    fing
    -0.66
     avenues
    -0.64
    ization
    -0.62
    cils
    -0.61
     bases
    -0.58
    ting
    -0.57
     attributes
    -0.57
    stanti
    -0.56
    POSITIVE LOGITS
     lèvres
    0.82
     extérieurs
    0.73
     oeufs
    0.70
     precisione
    0.69
     vectorielles
    0.67
    niosek
    0.67
     circulaire
    0.66
     navires
    0.66
     vœux
    0.66
     œufs
    0.65
    Activations Density 0.331%

    No Known Activations