© 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. 20-CLT-HP
    7. 77151
    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
    脚注の使い方
    -0.85
    KURZBESCHREIBUNG
    -0.77
     فريبيس
    -0.77
     صوتيه
    -0.76
    transQ
    -0.70
    EndProject
    -0.68
    Personendaten
    -0.67
     cherchés
    -0.66
    Sucesor
    -0.66
     }}$}
    -0.65
    POSITIVE LOGITS
     sticks
    0.35
    LoggerFactory
    0.34
     hay
    0.34
    \/
    0.33
     Asa
    0.33
     bambou
    0.33
     Jehová
    0.33
     tress
    0.32
    hay
    0.31
     tavola
    0.31
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.