© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 40327
    Prev
    Next
    INDEX
    Explanations

    Hal

    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
     Hal
    -1.61
    Hal
    -1.22
     hal
    -0.83
    o
    -0.53
     Dan
    -0.52
    HAL
    -0.50
    i
    -0.50
    a
    -0.49
     ni
    -0.49
     Hall
    -0.47
    POSITIVE LOGITS
     itſelf
    0.98
     Efq
    0.98
     ſeveral
    0.90
     myſelf
    0.90
     Monfieur
    0.88
     houſe
    0.86
     Houſe
    0.85
     ſmall
    0.84
     pleaſure
    0.84
     uſed
    0.83
    Activations Density 1.040%

    No Known Activations