© 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. 1-CLT-HP
    7. 15161
    Prev
    Next
    INDEX
    Explanations

    pregnant

    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
     Pregnant
    -1.29
     pregnant
    -1.28
    pregnant
    -1.12
     embarazada
    -0.73
     transférez
    -0.73
     oreilles
    -0.68
     cherchés
    -0.65
    AsStream
    -0.60
     flèche
    -0.59
     expectant
    -0.59
    POSITIVE LOGITS
    wieś
    0.53
    
    0.45
    GNUC
    0.45
    为止
    0.44
     laude
    0.44
     CURLOPT
    0.43
    encodeWith
    0.42
     WITH
    0.42
     ""],
    0.42
     bou
    0.42
    Activations Density 0.005%

    No Known Activations