© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97191
    Prev
    Next
    INDEX
    Explanations

    medical research and diseases

    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
     estekak
    -0.63
    JoinColumn
    -0.62
    <bos>
    -0.59
    EndInit
    -0.58
     EconPapers
    -0.58
     resourceCulture
    -0.57
     مرئيه
    -0.53
    IntoConstraints
    -0.51
     gynhyrchwyd
    -0.50
     ivelany
    -0.50
    POSITIVE LOGITS
     occafion
    0.60
    IZABETH
    0.57
    entier
    0.57
     Majefty
    0.54
     greateſt
    0.52
    fVar
    0.51
     ARD
    0.51
     spare
    0.50
     caufe
    0.48
    intervento
    0.48
    Activations Density 0.004%

    No Known Activations