© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2204
    Prev
    Next
    INDEX
    Explanations

    glutathione

    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
    athione
    -0.86
     glutathione
    -0.68
     &___
    -0.51
    ical
    -0.50
    ial
    -0.50
    land
    -0.48
    ing
    -0.48
    GIVEREF
    -0.48
    self
    -0.48
    ništ
    -0.46
    POSITIVE LOGITS
    पया
    0.59
     estimés
    0.57
    colgroup
    0.54
    ceous
    0.53
    )}</
    0.51
    gigi
    0.51
    protoc
    0.51
    }]
    0.50
     Diener
    0.49
    vaadin
    0.48
    Activations Density 0.007%

    No Known Activations