© 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. 5074
    Prev
    Next
    INDEX
    Explanations

    Human resources

    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
     متعلقه
    -0.56
     aDecoder
    -0.56
     незавершена
    -0.55
    ジュアル
    -0.53
     <=",
    -0.53
    NOPQRST
    -0.52
    expandindo
    -0.51
    OrBuilder
    -0.51
    IntoConstraints
    -0.51
    cancel
    -0.50
    POSITIVE LOGITS
    Tembelea
    0.49
     Planning
    0.48
    ņem
    0.48
     officielles
    0.47
     autorità
    0.46
    mutlich
    0.46
     fuoco
    0.46
     Roskov
    0.46
     dégâts
    0.45
     informacija
    0.45
    Activations Density 0.001%

    No Known Activations