© 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. 1-CLT-HP
    7. 9481
    Prev
    Next
    INDEX
    Explanations

    medical research

    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
     fu
    -0.50
    CodeAttribute
    -0.49
    Ber
    -0.49
     ta
    -0.48
     Ber
    -0.48
     ber
    -0.45
     Edi
    -0.45
     Cou
    -0.44
     tau
    -0.44
    ftn
    -0.43
    POSITIVE LOGITS
     nakalista
    0.86
    ItemBackground
    0.77
    SourceChecksum
    0.75
     OFDb
    0.70
     chrétiens
    0.69
     religieuses
    0.69
     marins
    0.68
     étoient
    0.68
    astify
    0.68
     âgées
    0.68
    Activations Density 0.113%

    No Known Activations