© 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. 1-CLT-HP
    7. 15042
    Prev
    Next
    INDEX
    Explanations

    cruise

    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
     cruise
    -2.09
     Cruise
    -1.85
    cruise
    -1.82
    Cruise
    -1.66
     cruises
    -1.66
     Cruises
    -1.42
     cruising
    -1.26
     CRU
    -1.13
     crucero
    -1.04
     cruze
    -0.95
    POSITIVE LOGITS
    ртка
    0.58
     geral
    0.54
     виправивши
    0.49
    UrlResolution
    0.47
    way
    0.46
     față
    0.45
    URIS
    0.44
    wha
    0.44
    wt
    0.43
    zaw
    0.42
    Activations Density 0.018%

    No Known Activations