© 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. 20-CLT-HP
    7. 77729
    Prev
    Next
    INDEX
    Explanations

    me

    np_max-act-logits · 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
    obos
    -0.51
    usercontent
    -0.49
     astore
    -0.47
     Clos
    -0.47
    i
    -0.46
    SourceChecksum
    -0.46
    SuspendLayout
    -0.45
     Hav
    -0.45
    完
    -0.44
     externi
    -0.44
    POSITIVE LOGITS
     CreateTagHelper
    0.61
    ObjectContext
    0.57
    peech
    0.57
     tremp
    0.57
     himſelf
    0.56
     Jefus
    0.56
     Efq
    0.55
    Smar
    0.54
    исленность
    0.54
    DropColumn
    0.54
    Activations Density 0.001%

    No Known Activations