© 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. 1-CLT-HP
    7. 14866
    Prev
    Next
    INDEX
    Explanations

    day

    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
    paž
    -0.49
     diputados
    -0.48
     dalamnya
    -0.47
    ifferentiated
    -0.47
     jäsen
    -0.46
    CopyWith
    -0.46
    timbangkan
    -0.46
     работой
    -0.46
     steder
    -0.45
    роид
    -0.45
    POSITIVE LOGITS
     ddelweddau
    0.65
    Autoritní
    0.63
     kasarigan
    0.61
     gecko
    0.61
     dragonfly
    0.58
     kittens
    0.58
     chicks
    0.58
     bral
    0.57
     lice
    0.56
     Ferns
    0.56
    Activations Density 0.007%

    No Known Activations