© 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. 1827
    Prev
    Next
    INDEX
    Explanations

    Scientific/technical language

    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
    "+
    
    -0.49
     Mr
    -0.47
     its
    -0.47
    "],
    -0.47
     his
    -0.44
     police
    -0.43
    /</
    -0.42
    </s>
    -0.42
     a
    -0.41
     ob
    -0.41
    POSITIVE LOGITS
     BoxDecoration
    0.86
     للمعارف
    0.82
    存于互联网档案馆
    0.77
     Toen
    0.71
     AttributeSet
    0.69
    Sucesor
    0.69
     getItemCount
    0.69
     Vikipedi
    0.69
     >=",
    0.68
     محفوظة
    0.68
    Activations Density 0.101%

    No Known Activations