© 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. 76901
    Prev
    Next
    INDEX
    Explanations

    Maxilla and dental procedures

    np_max-act-logits · 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
    miu
    -0.48
     Италијани
    -0.46
    mw
    -0.45
     muck
    -0.44
     الفلك
    -0.43
     musk
    -0.42
    Awe
    -0.42
     singularity
    -0.41
    ahead
    -0.41
    iprot
    -0.41
    POSITIVE LOGITS
     <>",
    0.77
    isDeleted
    0.58
    igli
    0.55
    
    0.55
    POUR
    0.55
     clearColor
    0.54
    verifyException
    0.54
    XmlAccessorType
    0.52
     doGet
    0.52
    fuhr
    0.52
    Activations Density 0.001%

    No Known Activations