© 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. 91608
    Prev
    Next
    INDEX
    Explanations

    sentence fragments

    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
     الحره
    -0.53
    Converters
    -0.47
    issons
    -0.43
     niets
    -0.43
     niks
    -0.42
    そこまで
    -0.42
     coś
    -0.41
     supper
    -0.39
     CreateTagHelper
    -0.39
     stubs
    -0.38
    POSITIVE LOGITS
    contentLoaded
    0.79
     prochaines
    0.79
     related
    0.77
     other
    0.74
    StreetMap
    0.73
    astify
    0.73
    DebuggerNonUser
    0.73
    autres
    0.71
    other
    0.70
    previous
    0.69
    Activations Density 0.001%

    No Known Activations