© 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. 40086
    Prev
    Next
    INDEX
    Explanations

    is

    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
    DeleteBehavior
    -0.92
     itſelf
    -0.82
    Filmografie
    -0.81
    èdia
    -0.81
     ―――――
    -0.80
    kháu
    -0.79
    onViewCreated
    -0.79
    RTDA
    -0.77
     propOrder
    -0.77
     سكانية
    -0.76
    POSITIVE LOGITS
     
    0.82
    ↵↵
    0.81
    <bos>
    0.74
    <eos>
    0.70
    ↵
    0.65
      
    0.59
     a
    0.55
    0.55
    The
    0.54
     an
    0.54
    Activations Density 0.138%
    No Known Activations