© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 90855
    Prev
    Next
    INDEX
    Explanations

    island/village

    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
     Theſe
    -1.02
     يتيمه
    -0.90
     island
    -0.90
     itſelf
    -0.89
    Enllaces
    -0.87
     Reſ
    -0.86
     Diſ
    -0.85
     myſelf
    -0.84
     ―――――
    -0.83
     wireType
    -0.81
    POSITIVE LOGITS
    ̣
    0.43
     with
    0.43
     o
    0.40
    la
    0.39
    le
    0.38
    ση
    0.38
    ring
    0.38
    >
    0.37
    ,
    0.37
    EndInit
    0.37
    Activations Density 0.122%

    No Known Activations