© 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. 0-CLT-HP
    7. 42724
    Prev
    Next
    INDEX
    Explanations

    news articles

    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
     hoje
    -0.48
    ofman
    -0.47
     parkir
    -0.47
     of
    -0.47
    edi
    -0.46
    AddTagHelper
    -0.44
     giáp
    -0.44
     frigo
    -0.43
     hoort
    -0.43
    ientôt
    -0.43
    POSITIVE LOGITS
    GEBURTSDATUM
    0.92
    styleType
    0.71
    DeleteBehavior
    0.71
     مرئيه
    0.70
     soils
    0.68
     Buildings
    0.68
    Sucesor
    0.68
    waters
    0.66
     Scalars
    0.66
     Waters
    0.65
    Activations Density 0.084%

    No Known Activations