© 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. 94017
    Prev
    Next
    INDEX
    Explanations

    deple

    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
     realize
    -0.91
     realise
    -0.88
     realized
    -0.85
     realizing
    -0.83
     realised
    -0.78
     realising
    -0.77
     realization
    -0.76
     realizes
    -0.73
     realisation
    -0.71
     realises
    -0.62
    POSITIVE LOGITS
     automatiques
    0.60
     kasarigan
    0.57
    urlpatterns
    0.56
     rady
    0.53
     useRouter
    0.53
    SerializedName
    0.52
    odyear
    0.50
    versiti
    0.50
    دانشنامهٔ
    0.50
    iedene
    0.50
    Activations Density 0.017%

    No Known Activations