© 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. 43189
    Prev
    Next
    INDEX
    Explanations

    definitive

    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
     dominant
    -0.91
    dominant
    -0.82
     Dominant
    -0.73
     pulito
    -0.62
     adaptée
    -0.62
     recessive
    -0.60
     vettore
    -0.57
    ired
    -0.57
     definitive
    -0.57
     déploy
    -0.57
    POSITIVE LOGITS
    ValueGeneration
    0.67
     calendriers
    0.61
    oa̍t
    0.54
    %)$
    0.51
    Comté
    0.51
    awtextra
    0.50
     Dyck
    0.50
     IBOutlet
    0.49
     Accueil
    0.49
    EDEFAULT
    0.49
    Activations Density 0.120%

    No Known Activations