© 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. 0-CLT-HP
    7. 95318
    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
     positifs
    -1.18
     itſelf
    -1.16
     positive
    -1.10
    positive
    -1.10
    Positive
    -1.08
     Monfieur
    -1.06
     positivas
    -1.05
     purpoſe
    -1.03
     myſelf
    -1.02
     feroit
    -1.01
    POSITIVE LOGITS
     for
    0.58
    ,
    0.58
     /
    0.56
     (
    0.55
    .
    0.55
    /
    0.54
     or
    0.53
    ally
    0.53
     and
    0.52
     U
    0.52
    Activations Density 0.081%

    No Known Activations