© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5112
    Prev
    Next
    INDEX
    Explanations

    relative pronouns

    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
    κει
    -0.59
    SourceChecksum
    -0.56
     auroit
    -0.54
    complexType
    -0.50
     descobri
    -0.49
    __).
    -0.48
    ]=>
    -0.48
     itſelf
    -0.48
     ritrov
    -0.47
     realising
    -0.47
    POSITIVE LOGITS
     choose
    0.73
     try
    0.71
     dare
    0.66
     fail
    0.66
     chooses
    0.65
     ask
    0.64
     decide
    0.61
     take
    0.60
     tell
    0.58
     offend
    0.58
    Activations Density 0.003%

    No Known Activations