© 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. 1-CLT-HP
    7. 13637
    Prev
    Next
    INDEX
    Explanations

    Scientific names and bacteria

    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
    ัด
    -0.45
     gepubliceerd
    -0.45
     Read
    -0.43
     read
    -0.43
    estand
    -0.41
    gettes
    -0.40
    ifolia
    -0.40
    ximation
    -0.40
     consentement
    -0.40
    亥
    -0.40
    POSITIVE LOGITS
    migrationBuilder
    0.87
    ContentAsync
    0.78
    ngdoc
    0.77
    PYX
    0.66
     Economía
    0.65
     HasFactory
    0.64
     onCancelled
    0.63
     '\\;'
    0.62
     snippetHide
    0.62
     kvar
    0.61
    Activations Density 0.074%

    No Known Activations