© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93562
    Prev
    Next
    INDEX
    Explanations

    actions, cleaning, archaic formal words

    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
     shall
    -1.16
    shall
    -1.13
     Shall
    -1.02
     flush
    -0.97
     shalt
    -0.94
     SHALL
    -0.89
    Shall
    -0.88
     flushing
    -0.87
     Flush
    -0.81
    Flush
    -0.81
    POSITIVE LOGITS
     fit
    0.59
    tling
    0.59
    tanleria
    0.57
    Jeografia
    0.57
     find
    0.55
    ופר
    0.54
    arbox
    0.54
    الصفحه
    0.54
     past
    0.53
    erle
    0.52
    Activations Density 1.642%

    No Known Activations