© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1815
    Prev
    Next
    INDEX
    Explanations

    phia

    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
    uries
    -1.85
    phia
    -0.85
    RegressionTest
    -0.63
    urie
    -0.61
     mergeFrom
    -0.58
    umerable
    -0.57
    letoe
    -0.53
    atellite
    -0.52
    nader
    -0.52
     getItemCount
    -0.52
    POSITIVE LOGITS
     Efq
    0.84
    ſelf
    0.81
     Monfieur
    0.80
     houſe
    0.75
     myſelf
    0.74
     pleaſure
    0.74
     itſelf
    0.72
     Majefty
    0.70
     poffe
    0.70
     purpoſe
    0.69
    Activations Density 0.325%

    No Known Activations