© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 43575
    Prev
    Next
    INDEX
    Explanations

    engineering

    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
     réfrig
    -0.83
     lumineuse
    -0.82
     vectorielles
    -0.81
     quantités
    -0.81
     normaux
    -0.77
     étroite
    -0.77
     nucléaire
    -0.76
     vectorielle
    -0.76
     imprimée
    -0.76
     pitié
    -0.75
    POSITIVE LOGITS
    able
    0.76
    ly
    0.69
    land
    0.68
    ling
    0.66
    er
    0.59
    ring
    0.59
    ese
    0.59
    minton
    0.59
    ase
    0.58
    theless
    0.58
    Activations Density 1.025%

    No Known Activations