© 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. 8937
    Prev
    Next
    INDEX
    Explanations

    speaking

    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
    :✨
    -0.63
    EDEFAULT
    -0.58
    seende
    -0.57
     sermon
    -0.57
    lgari
    -0.55
    parsedMessage
    -0.54
     poem
    -0.53
    Personendaten
    -0.51
     jadx
    -0.50
    UVWXYZ
    -0.50
    POSITIVE LOGITS
     enfans
    0.51
     vacacionales
    0.50
    atórios
    0.49
     irmã
    0.45
     Raton
    0.44
     deputado
    0.44
     sœur
    0.44
     collègues
    0.44
     bague
    0.44
     emprego
    0.44
    Activations Density 0.007%

    No Known Activations