© 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. 0-CLT-HP
    7. 42681
    Prev
    Next
    INDEX
    Explanations

    specific references

    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
    __':
    -0.85
    kháu
    -0.76
     Gav
    -0.66
     gjø
    -0.62
     estacionamiento
    -0.61
    awtextra
    -0.61
     lifestyle
    -0.59
    خرى
    -0.59
    !*\
    -0.59
    SBATCH
    -0.59
    POSITIVE LOGITS
     Vikipedi
    0.52
    postsleuth
    0.49
    ęty
    0.47
     heparin
    0.47
     retrograde
    0.47
     kites
    0.47
     giro
    0.46
    cahontas
    0.46
    SPP
    0.46
    copyWith
    0.46
    Activations Density 0.165%

    No Known Activations