© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 95644
    Prev
    Next
    INDEX
    Explanations

    research

    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
    Negative Logits
     researcher
    -1.06
     researchers
    -0.98
     Researcher
    -0.91
    ſelves
    -0.89
     itſelf
    -0.82
     Majefty
    -0.81
     Houſe
    -0.81
     Researchers
    -0.79
     pleaſure
    -0.78
     myſelf
    -0.78
    POSITIVE LOGITS
     Réponses
    0.56
    เร็
    0.48
     Tom
    0.48
    NameInMap
    0.47
     
    0.45
     "..\..\..\
    0.45
     Greg
    0.44
     ujednoznacz
    0.43
    StylePriority
    0.42
    UniformLocation
    0.42
    Activations Density 0.134%

    No Known Activations