© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3602
    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
    )))),
    -0.54
     wilden
    -0.50
    lored
    -0.49
     to
    -0.48
    rawtypes
    -0.47
     breakers
    -0.46
    IonicModule
    -0.46
     smears
    -0.45
    )))))
    -0.44
     bundles
    -0.43
    POSITIVE LOGITS
     finish
    0.98
     يتيمه
    0.95
     tartalomajánló
    0.74
    finish
    0.73
     FINISH
    0.71
     resourceCulture
    0.70
    MessageTagHelper
    0.70
    цездатний
    0.70
     ويكيميديا
    0.68
     arrive
    0.67
    Activations Density 0.003%

    No Known Activations