© 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. 9835
    Prev
    Next
    INDEX
    Explanations

    microscopy

    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
     تضيفلها
    -0.82
    تقاوى
    -0.69
    homonymie
    -0.68
    Autoritní
    -0.65
    Chham
    -0.65
    ⓧ
    -0.65
     Administrativna
    -0.63
     виправивши
    -0.60
    bewerken
    -0.57
     autorytatywna
    -0.56
    POSITIVE LOGITS
    enschutzer
    0.48
     signal
    0.48
     Win
    0.47
    lorette
    0.47
     Brent
    0.45
     Wo
    0.44
     GIF
    0.44
     Internet
    0.44
    mal
    0.43
     living
    0.43
    Activations Density 0.116%

    No Known Activations