© 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. 14365
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     réglable
    -0.54
     refroidissement
    -0.53
     تضيفلها
    -0.52
     Weighted
    -0.52
     Thermal
    -0.52
     médicament
    -0.49
     Neg
    -0.49
     Strada
    -0.48
     paysage
    -0.48
     Mechanical
    -0.48
    POSITIVE LOGITS
    tanleria
    0.67
     "
    0.56
     “
    0.56
    oredCriteria
    0.54
     Roskov
    0.51
    homonymie
    0.51
    كويكب
    0.51
    ]<<"
    0.50
    —"
    0.50
     ‘
    0.50
    Activations Density 0.001%

    No Known Activations