© 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. 0-CLT-HP
    7. 94314
    Prev
    Next
    INDEX
    Explanations

    abortion

    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
     abortion
    -0.81
    cel
    -0.75
    Cel
    -0.61
     Lon
    -0.61
     abortions
    -0.60
     cel
    -0.59
     aborto
    -0.59
    mybatisplus
    -0.57
     Bill
    -0.55
    CEL
    -0.55
    POSITIVE LOGITS
    astéroïdes
    0.69
    ably
    0.61
    ed
    0.60
    atically
    0.58
     '\\;'
    0.57
    iously
    0.56
    oos
    0.55
    liness
    0.54
    setEditable
    0.54
    standing
    0.54
    Activations Density 0.282%

    No Known Activations