© 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. 5-CLT-HP
    7. 4951
    Prev
    Next
    INDEX
    Explanations

    identification/codes

    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
     nakalista
    -0.75
     protoimpl
    -0.75
    __':
    -0.69
     חיצוניים
    -0.67
    انيف
    -0.66
     Waray
    -0.65
    __':
    -0.65
    :✨
    -0.64
    
    -0.62
    Lähteet
    -0.61
    POSITIVE LOGITS
     desen
    0.46
     chi̍t
    0.42
    jboss
    0.41
     Bjør
    0.41
    jela
    0.41
    Referințe
    0.41
    buttonBar
    0.40
     Ressource
    0.40
    ouan
    0.40
    荞
    0.40
    Activations Density 0.001%

    No Known Activations