© 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. 5-CLT-HP
    7. 5609
    Prev
    Next
    INDEX
    Explanations

    medical

    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
     AssemblyCulture
    -0.75
    AndEndTag
    -0.74
    tvguidetime
    -0.72
    GEBURTSDATUM
    -0.68
    Focus
    -0.66
    脚注の使い方
    -0.66
    DataAnnotations
    -0.66
     Focused
    -0.65
     Zä
    -0.65
     étoient
    -0.65
    POSITIVE LOGITS
     informação
    0.46
     Италијани
    0.46
    าม
    0.43
     $?
    0.43
    erialized
    0.42
     information
    0.40
     aires
    0.40
     so
    0.40
    0.40
    ishable
    0.40
    Activations Density 0.005%

    No Known Activations