© 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. 90653
    Prev
    Next
    INDEX
    Explanations

    castle

    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
     Castle
    -0.94
     circle
    -0.92
    Castle
    -0.88
     castle
    -0.86
     justice
    -0.83
     Circle
    -0.82
     Justice
    -0.81
    circle
    -0.79
     CASTLE
    -0.79
     FetchType
    -0.77
    POSITIVE LOGITS
    getPlayer
    0.51
    player
    0.51
     tille
    0.48
    bro
    0.48
    mar
    0.47
     indietro
    0.46
     umano
    0.46
     regionale
    0.45
    ofold
    0.45
     ambientale
    0.45
    Activations Density 0.114%

    No Known Activations