© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 45479
    Prev
    Next
    INDEX
    Explanations

    allies

    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
     davanti
    -0.60
     chré
    -0.59
     preghi
    -0.59
     femininas
    -0.59
     démocr
    -0.57
     forêt
    -0.56
     attravers
    -0.55
    '
    -0.55
     diante
    -0.54
     andato
    -0.52
    POSITIVE LOGITS
    ly
    1.47
    LY
    0.93
    mente
    0.86
    ness
    0.73
    nya
    0.73
    tonsoft
    0.71
    theless
    0.66
    nesses
    0.65
    lyl
    0.65
    lyt
    0.63
    Activations Density 1.154%

    No Known Activations