© 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. 5235
    Prev
    Next
    INDEX
    Explanations

    followed

    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
     Well
    -0.54
    moga
    -0.52
     Des
    -0.51
    :
    -0.51
     Ten
    -0.51
     To
    -0.51
     Does
    -0.50
     Knows
    -0.50
     proves
    -0.50
     Romano
    -0.50
    POSITIVE LOGITS
     estekak
    0.88
     autorytatywna
    0.73
     himo
    0.63
     odkazy
    0.62
     سكانية
    0.59
    Зноскі
    0.57
     تانيه
    0.56
    Obrázky
    0.54
    elemField
    0.54
    Personendaten
    0.51
    Activations Density 0.002%

    No Known Activations