© 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. 1-CLT-HP
    7. 10028
    Prev
    Next
    INDEX
    Explanations

    same

    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
     AssemblyCulture
    -0.77
     admi
    -0.73
    EndGlobalSection
    -0.73
     saites
    -0.73
    IUrlHelper
    -0.71
    SourceChecksum
    -0.66
     Roskov
    -0.66
    طلحات
    -0.65
    SharedDtor
    -0.65
    FieldNumber
    -0.64
    POSITIVE LOGITS
    plat
    0.44
    express
    0.43
     rendez
    0.41
    xtures
    0.41
    totalSupply
    0.40
    viva
    0.39
    󠁢
    0.39
    OUS
    0.38
    height
    0.38
    RIG
    0.38
    Activations Density 0.045%

    No Known Activations