© 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. 5-CLT-HP
    7. 5608
    Prev
    Next
    INDEX
    Explanations

    code/technical documents

    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
     prisonniers
    -0.55
    asticity
    -0.54
     RestTemplate
    -0.53
     polizia
    -0.52
     prêtres
    -0.51
    cemia
    -0.50
    вості
    -0.50
    TargetException
    -0.48
     renseignements
    -0.48
     químicos
    -0.47
    POSITIVE LOGITS
    WriteTagHelper
    0.64
    Халык
    0.59
    ModelSerializer
    0.57
    scriptcase
    0.55
    awakeFromNib
    0.51
    iprot
    0.51
    basicConfig
    0.51
    MemoryWarning
    0.50
    Portale
    0.50
     Garden
    0.50
    Activations Density 0.001%

    No Known Activations