© 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. 1-CLT-HP
    7. 8759
    Prev
    Next
    INDEX
    Explanations

    them

    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
     ferons
    -0.75
     découver
    -0.69
     détru
    -0.69
     pauvres
    -0.67
     démocr
    -0.66
     aveug
    -0.64
     étro
    -0.63
     réguli
    -0.63
     découvertes
    -0.63
     déchir
    -0.62
    POSITIVE LOGITS
     mobilize
    0.81
    antaine
    0.80
     circumcision
    0.75
     remission
    0.72
     mobilization
    0.72
     commutation
    0.71
     uſe
    0.71
     superposition
    0.70
     coö
    0.70
     mobili
    0.70
    Activations Density 0.110%

    No Known Activations