© 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. 72365
    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
     Wicidata
    -0.62
    లాలు
    -0.61
    الحياه
    -0.60
     defaultstate
    -0.59
    Географи
    -0.59
     referenties
    -0.58
     OFDb
    -0.58
     utafitiHapana
    -0.57
    StoryboardSegue
    -0.57
     nhàng
    -0.56
    POSITIVE LOGITS
     Brill
    0.53
     الاطلاع
    0.45
     virtual
    0.45
    virtual
    0.43
     governor
    0.43
     Governor
    0.43
     annihilation
    0.42
     Fim
    0.42
     ash
    0.40
    êr
    0.40
    Activations Density 0.017%

    No Known Activations