© 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. 1-CLT-HP
    7. 11808
    Prev
    Next
    INDEX
    Explanations

    shut

    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
     shut
    -1.84
     Shut
    -1.68
    shut
    -1.65
     SHUT
    -1.52
    Shut
    -1.49
     shuts
    -1.33
    SHUT
    -1.27
     shuttle
    -1.27
     Shuttle
    -1.22
     shutting
    -1.20
    POSITIVE LOGITS
    tin
    0.66
    ters
    0.61
    tled
    0.57
    ting
    0.55
    cock
    0.52
    ten
    0.51
    ted
    0.50
    tered
    0.50
    teri
    0.50
    tied
    0.48
    Activations Density 0.010%

    No Known Activations