© 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. 1618
    Prev
    Next
    INDEX
    Explanations

    Future tense/possibility

    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
     all
    -1.73
    all
    -1.34
     ALL
    -1.16
     his
    -1.10
    All
    -1.05
     semua
    -1.04
     each
    -1.02
     All
    -1.01
    ALL
    -0.95
     allemaal
    -0.94
    POSITIVE LOGITS
     have
    1.09
    have
    0.83
     bave
    0.83
     haven
    0.69
    Have
    0.69
     preside
    0.69
     were
    0.69
    ]){
    
    0.67
     HAVE
    0.66
    dań
    0.66
    Activations Density 0.069%

    No Known Activations