© 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. 20-CLT-HP
    7. 78063
    Prev
    Next
    INDEX
    Explanations

    Negative prefixes/banning

    np_max-act-logits · 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
    いざ
    -0.44
     posé
    -0.43
     vendido
    -0.43
     tombé
    -0.43
    ósitos
    -0.43
     découver
    -0.42
     chauss
    -0.41
     sẻ
    -0.40
     loja
    -0.40
     mélanger
    -0.40
    POSITIVE LOGITS
     dis
    1.02
     discourage
    1.00
     discou
    1.00
     dissu
    0.94
     ban
    0.94
     discouraged
    0.91
     prohibit
    0.91
     forbid
    0.88
     forbidding
    0.85
     bans
    0.85
    Activations Density 0.000%

    No Known Activations