© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 8981
    Prev
    Next
    INDEX
    Explanations

    culum

    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
     تانيه
    -0.90
    expandindo
    -0.87
     estekak
    -0.75
    rungsseite
    -0.73
     betweenstory
    -0.73
     debout
    -0.70
    culum
    -0.68
    Демографія
    -0.66
     تضيفلها
    -0.65
    PreferredItem
    -0.64
    POSITIVE LOGITS
    na
    0.52
    Zeneca
    0.48
    fold
    0.47
    FSC
    0.45
    Izvori
    0.44
     hin
    0.42
    GraphicsUnit
    0.40
    dolu
    0.40
    ském
    0.40
    ness
    0.39
    Activations Density 0.060%

    No Known Activations