© 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. 4-CLT-HP
    7. 1146
    Prev
    Next
    INDEX
    Explanations

    Medical patients/cases

    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
    ValueStyle
    -0.60
     NDL
    -0.56
    bbene
    -0.56
    complexContent
    -0.55
    ngdoc
    -0.55
    AnimationsModule
    -0.54
    PhysRevD
    -0.52
     exclusivo
    -0.52
     komma
    -0.52
     defStyleAttr
    -0.51
    POSITIVE LOGITS
    attan
    0.53
    Diweddarwch
    0.53
     saw
    0.52
     sees
    0.51
     see
    0.50
     includes
    0.50
    <bos>
    0.50
     did
    0.49
     was
    0.48
     treated
    0.47
    Activations Density 0.009%

    No Known Activations