© 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. 71832
    Prev
    Next
    INDEX
    Explanations

    code/technical snippets

    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
    migrationBuilder
    -0.75
     '\\;'
    -0.73
    Personensuche
    -0.70
     AppCompatTheme
    -0.69
    oredCriteria
    -0.65
    دانشنامهٔ
    -0.64
     wireType
    -0.64
     DbSet
    -0.62
     Reviewing
    -0.62
    protoimpl
    -0.61
    POSITIVE LOGITS
     read
    0.67
     متعلقه
    0.61
    TagMode
    0.57
    read
    0.49
     surla
    0.47
     watch
    0.45
     reads
    0.45
     approach
    0.45
     AdapterView
    0.43
    ŕ
    0.42
    Activations Density 0.000%

    No Known Activations