© 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. 4-CLT-HP
    7. 617
    Prev
    Next
    INDEX
    Explanations

    depression/antidepressants

    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
     PEDRO
    -0.52
     elongation
    -0.51
     secrets
    -0.47
    ei
    -0.47
    iocene
    -0.47
    Portale
    -0.47
    EndContext
    -0.46
    ício
    -0.46
    iostream
    -0.46
     treaties
    -0.46
    POSITIVE LOGITS
     tartalomajánló
    0.64
    ReusableCell
    0.63
     समीक्षक
    0.61
    ArgsConstructor
    0.60
    own
    0.59
    TagMode
    0.57
    antly
    0.57
    antor
    0.56
     InputDecoration
    0.56
     تضيفلها
    0.54
    Activations Density 0.001%

    No Known Activations