© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 73523
    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
     scattata
    -0.67
     credere
    -0.63
     الاطلاع
    -0.56
     riuscito
    -0.53
     run
    -0.52
    put
    -0.49
    Run
    -0.49
     runs
    -0.49
     moderni
    -0.48
    bbene
    -0.48
    POSITIVE LOGITS
    +#+#
    0.71
     ComVisible
    0.66
    tvguidetime
    0.62
     Мексичка
    0.62
    Omg
    0.60
    rinfo
    0.59
     Touchable
    0.59
    oshima
    0.58
     betweenstory
    0.58
    ruptedException
    0.57
    Activations Density 0.000%

    No Known Activations