© 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. 90473
    Prev
    Next
    INDEX
    Explanations

    movies, or tightening mechanisms

    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
     rekening
    -0.66
    ergies
    -0.66
     quotas
    -0.64
     intensification
    -0.63
     tightening
    -0.63
     tightened
    -0.63
     Pyrr
    -0.60
    Grath
    -0.59
     dormitórios
    -0.59
     Equinox
    -0.59
    POSITIVE LOGITS
    OrBuilder
    0.52
    ⓧ
    0.52
     useRouter
    0.50
    InstrumentedTest
    0.48
    Atsauces
    0.44
    
    0.42
    GeneratedMessage
    0.41
     band
    0.41
     protoimpl
    0.41
    ))=\
    0.40
    Activations Density 0.036%

    No Known Activations