© 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. 5-CLT-HP
    7. 5002
    Prev
    Next
    INDEX
    Explanations

    to

    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
    DeleteBehavior
    -0.67
     Specifically
    -0.66
     للمعارف
    -0.61
    Vidite
    -0.60
     <<<<<<<<<<<<<<
    -0.59
    Specifically
    -0.59
    NewUrlParser
    -0.57
    GenerationType
    -0.55
     bepaald
    -0.54
     Offisielt
    -0.54
    POSITIVE LOGITS
     carrying
    0.57
    الإنجليزية
    0.56
     offrant
    0.53
     promoting
    0.53
     creating
    0.52
     romanos
    0.50
     eliminating
    0.50
     ofreciendo
    0.49
     Josephus
    0.48
     who
    0.47
    Activations Density 0.000%

    No Known Activations