© 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. 4-CLT-HP
    7. 195
    Prev
    Next
    INDEX
    Explanations

    medical/scientific texts

    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
    UserScript
    -0.65
    GEBURTSDATUM
    -0.61
     препратки
    -0.61
    Personensuche
    -0.60
    ScopeManager
    -0.57
    CreateMap
    -0.57
    Portale
    -0.53
     Lumen
    -0.52
     Deve
    -0.51
    WebElementEntity
    -0.51
    POSITIVE LOGITS
    ’
    1.29
    '
    0.88
     
    0.66
     have
    0.58
     wanted
    0.57
     believe
    0.56
    ‘
    0.56
     want
    0.56
     think
    0.56
     will
    0.55
    Activations Density 0.003%

    No Known Activations