© 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. 42740
    Prev
    Next
    INDEX
    Explanations

    Describing something, related art

    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
    rungsseite
    -1.16
    oneofs
    -0.77
    MigrationBuilder
    -0.73
     autorytatywna
    -0.72
     onBind
    -0.72
    (!__
    -0.68
     ujednoznacz
    -0.66
     Réponses
    -0.66
     createState
    -0.64
     defaultstate
    -0.63
    POSITIVE LOGITS
    cipital
    0.52
     modality
    0.50
     cohort
    0.48
     Arta
    0.48
     polymorphism
    0.47
     intramuscular
    0.46
    Eloquent
    0.45
    ResourceBundle
    0.45
     causation
    0.45
     Cohort
    0.45
    Activations Density 0.437%

    No Known Activations