© 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. 93794
    Prev
    Next
    INDEX
    Explanations

    module

    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
     OFDb
    -0.52
    arky
    -0.48
     engagement
    -0.48
    ISTERS
    -0.46
    ılığı
    -0.45
     Италијани
    -0.44
    lasty
    -0.44
     Woodbury
    -0.44
     aught
    -0.44
    getProject
    -0.43
    POSITIVE LOGITS
     OnInit
    0.61
     contextLoads
    0.59
    AnimationsModule
    0.58
    URLException
    0.54
     Delia
    0.54
    Données
    0.54
    XtraReports
    0.53
    DaoImpl
    0.52
     imageNamed
    0.52
     Daniel
    0.51
    Activations Density 0.011%

    No Known Activations