© 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. 8906
    Prev
    Next
    INDEX
    Explanations

    used

    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
     AssemblyCulture
    -0.50
    inium
    -0.49
    octanol
    -0.47
    chism
    -0.47
     utilisés
    -0.47
    morgen
    -0.47
     détruit
    -0.46
     entrevistas
    -0.45
     sqlalchemy
    -0.44
     entretien
    -0.44
    POSITIVE LOGITS
     for
    0.62
     leaſt
    0.59
     Moslem
    0.57
    PyExc
    0.57
     vulga
    0.57
     Pharisees
    0.56
    dresser
    0.55
     ſtate
    0.55
     beſt
    0.55
     themſelves
    0.55
    Activations Density 0.002%

    No Known Activations