© 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. 5-CLT-HP
    7. 5467
    Prev
    Next
    INDEX
    Explanations

    cinnamon

    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
     smelling
    -1.00
     smelled
    -0.96
     smells
    -0.83
     smell
    -0.82
     aromas
    -0.73
     scents
    -0.71
     fragrant
    -0.67
     smelt
    -0.67
     aromatic
    -0.66
     odors
    -0.65
    POSITIVE LOGITS
    出版年
    0.88
    principalTable
    0.59
    CPtr
    0.57
    Personensuche
    0.56
    TestingModule
    0.56
    الإنجليزية
    0.54
     exposición
    0.54
    ัติ
    0.54
     nakalista
    0.52
    stärke
    0.51
    Activations Density 0.005%

    No Known Activations