© 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. 0-CLT-HP
    7. 93654
    Prev
    Next
    INDEX
    Explanations

    Aviation

    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
     sang
    -0.47
    acio
    -0.45
    aggi
    -0.45
    ace
    -0.44
    tev
    -0.44
    kopf
    -0.44
     an
    -0.44
     bal
    -0.43
    ICIAN
    -0.43
     som
    -0.43
    POSITIVE LOGITS
     purpoſe
    0.69
     doubtnut
    0.65
     تضيفلها
    0.63
    queryInterface
    0.63
    ForRow
    0.61
     Jefus
    0.61
    principalTable
    0.61
     inimes
    0.61
     ansatte
    0.60
     Diſ
    0.60
    Activations Density 0.091%

    No Known Activations