© 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. 306
    Prev
    Next
    INDEX
    Explanations

    Cannabis

    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
    ing
    -0.60
    ed
    -0.56
    ig
    -0.53
    outons
    -0.46
    ize
    -0.45
    ian
    -0.44
    house
    -0.44
    M
    -0.44
    ward
    -0.43
     zufolge
    -0.43
    POSITIVE LOGITS
     sativa
    0.79
     Roskov
    0.76
    protoimpl
    0.76
     كومونز
    0.73
    awtextra
    0.64
     متعلقه
    0.63
    पया
    0.63
     تضيفلها
    0.62
    findpost
    0.60
    Portail
    0.58
    Activations Density 0.005%

    No Known Activations