© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97072
    Prev
    Next
    INDEX
    Explanations

    incidents/event reports

    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
    CloseOperation
    -0.78
    oredCriteria
    -0.71
     Efq
    -0.69
     epidemics
    -0.64
    __':
    -0.64
    OrBuilder
    -0.64
     considérons
    -0.64
     referenties
    -0.64
    WebVitals
    -0.63
    __':
    -0.63
    POSITIVE LOGITS
     électroniques
    0.50
     artificiales
    0.43
    inture
    0.43
     puissent
    0.42
     dezembro
    0.41
     umana
    0.40
     juridiques
    0.40
     salvación
    0.40
     humaines
    0.39
     Palatine
    0.39
    Activations Density 0.046%

    No Known Activations