© 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. 4614
    Prev
    Next
    INDEX
    Explanations

    to

    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
    aronder
    -0.60
    Captor
    -0.56
     ams
    -0.53
    complexType
    -0.52
    ]")]
    -0.51
    urlpatterns
    -0.50
     huge
    -0.50
     celle
    -0.50
     highly
    -0.50
    дик
    -0.50
    POSITIVE LOGITS
     Roskov
    0.61
     funcionales
    0.59
     Function
    0.58
     simplesmente
    0.57
     kasarigan
    0.56
     function
    0.56
     Waray
    0.55
     peines
    0.54
    konomi
    0.54
     blessures
    0.53
    Activations Density 0.001%

    No Known Activations