© 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. 92680
    Prev
    Next
    INDEX
    Explanations

    family

    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
    FormTagHelper
    -0.58
     aéreas
    -0.57
     noires
    -0.54
     sauvages
    -0.53
     legais
    -0.53
     artesanales
    -0.52
     avoient
    -0.52
     gratuits
    -0.52
     blessés
    -0.51
     locaux
    -0.51
    POSITIVE LOGITS
    Geplaatst
    0.58
    pherals
    0.56
    OrNil
    0.54
    rativa
    0.54
    Autoritní
    0.54
     Ruz
    0.54
    losing
    0.53
    elemField
    0.53
    Démographie
    0.53
     losing
    0.52
    Activations Density 0.001%

    No Known Activations