© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 90661
    Prev
    Next
    INDEX
    Explanations

    organizations

    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
     Institute
    -0.59
     universe
    -0.50
    rufe
    -0.50
    Institute
    -0.50
    åd
    -0.49
     institute
    -0.49
    รง
    -0.47
     κό
    -0.47
     onData
    -0.47
    ят
    -0.46
    POSITIVE LOGITS
     يتيمه
    0.84
    Personensuche
    0.72
    ConstraintMaker
    0.71
     архивлан
    0.68
     MonoBehaviour
    0.67
    Cyfeiriadau
    0.66
     متعلقه
    0.66
    sproz
    0.63
    GEBURTSDATUM
    0.60
     jspb
    0.59
    Activations Density 0.104%

    No Known Activations