© 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. 4483
    Prev
    Next
    INDEX
    Explanations

    thrive

    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
    IsMutable
    -0.92
    ThroughAttribute
    -0.90
    expandindo
    -0.84
    GEBURTSDATUM
    -0.83
     Roskov
    -0.82
    ViewFeatures
    -0.82
     disambiguazione
    -0.81
    Искәрмәләр
    -0.80
    Portail
    -0.79
     متعلقه
    -0.78
    POSITIVE LOGITS
    .
    0.54
     in
    0.48
    ModelAttribute
    0.45
    urg
    0.44
     on
    0.41
    paddingBottom
    0.40
     before
    0.38
     come
    0.37
    way
    0.37
    but
    0.37
    Activations Density 0.000%

    No Known Activations