© 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. 94433
    Prev
    Next
    INDEX
    Explanations

    find

    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
     finding
    -0.88
     find
    -0.87
     finds
    -0.77
    finding
    -0.65
    Finding
    -0.63
    enumi
    -0.61
     encontrar
    -0.59
     found
    -0.58
    Find
    -0.57
     trouver
    -0.57
    POSITIVE LOGITS
     judiciaire
    0.75
     NDEBUG
    0.75
     grève
    0.69
     circonst
    0.68
     gouvernements
    0.67
     pandémie
    0.66
     nôtre
    0.64
     sfera
    0.63
     mijne
    0.63
     fréquence
    0.62
    Activations Density 0.148%

    No Known Activations