© 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. 0-CLT-HP
    7. 95725
    Prev
    Next
    INDEX
    Explanations

    species

    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
     species
    -1.57
    species
    -1.29
     Species
    -1.27
    Species
    -1.22
     SPECIES
    -1.00
     especies
    -0.98
     espèces
    -0.94
     espécies
    -0.84
    SPECIES
    -0.82
     specie
    -0.76
    POSITIVE LOGITS
     onCreateView
    0.84
    DoubleQuotes
    0.83
    ReusableCell
    0.78
     Houſe
    0.77
    Gön
    0.77
     الحره
    0.76
     Picchu
    0.75
     chests
    0.72
     octaves
    0.71
     constexpr
    0.71
    Activations Density 2.024%

    No Known Activations