© 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. 93914
    Prev
    Next
    INDEX
    Explanations

    psychiatric

    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
    ScopeManager
    -1.05
     vectorielles
    -1.00
     réguli
    -0.99
    HasAnnotation
    -0.94
     Roskov
    -0.93
     CURIAM
    -0.90
     vermelhas
    -0.88
     négociations
    -0.87
     financières
    -0.84
    SharedDtor
    -0.81
    POSITIVE LOGITS
    s
    0.88
    ization
    0.52
    sve
    0.52
    m
    0.50
    ly
    0.49
    ize
    0.48
    sis
    0.45
     guidance
    0.45
    ness
    0.45
     defense
    0.45
    Activations Density 0.066%

    No Known Activations