© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 6074
    Prev
    Next
    INDEX
    Explanations

    be not

    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
    Negative Logits
     الحره
    -0.73
    icksburg
    -0.63
    saraba
    -0.60
     Winaray
    -0.60
     leaſt
    -0.59
     themſelves
    -0.59
     well
    -0.57
     ſeveral
    -0.56
     whoſe
    -0.56
    migrationBuilder
    -0.55
    POSITIVE LOGITS
     estekak
    0.72
     tam
    0.69
     wasted
    0.59
     lost
    0.57
     altered
    0.51
     confused
    0.51
     disturbed
    0.50
     obstructed
    0.50
     forgotten
    0.49
     overloaded
    0.48
    Activations Density 0.003%

    No Known Activations